no code implementations • LREC 2012 • James Clarke, Vivek Srikumar, Mark Sammons, Dan Roth
Natural Language Processing continues to grow in popularity in a range of research and commercial applications, yet managing the wide array of potential NLP components remains a difficult problem.
no code implementations • TACL 2013 • Vivek Srikumar, Dan Roth
This paper introduces the problem of predicting semantic relations expressed by prepositions and develops statistical learning models for predicting the relations, their arguments and the semantic types of the arguments.
no code implementations • 24 May 2013 • Vivek Srikumar, Dan Roth
We describe an inventory of semantic relations that are expressed by prepositions.
no code implementations • TACL 2014 • Alla Rozovskaya, Dan Roth
This paper identifies and examines the key principles underlying building a state-of-the-art grammatical error correction system.
no code implementations • LREC 2014 • Hao Wu, Zhiye Fei, Aaron Dai, Mark Sammons, Dan Roth, Stephen Mayhew
Natural Language Processing (NLP) continues to grow in popularity in a range of research and commercial applications.
no code implementations • TACL 2015 • Subhro Roy, Tim Vieira, Dan Roth
In order to address these quantitative reasoning problems we first develop a computational approach which we show to successfully recognize and normalize textual expressions of quantities.
no code implementations • 8 Jun 2015 • Ching-pei Lee, Kai-Wei Chang, Shyam Upadhyay, Dan Roth
Training structured prediction models is time-consuming.
1 code implementation • TACL 2015 • John Wieting, Mohit Bansal, Kevin Gimpel, Karen Livescu, Dan Roth
The Paraphrase Database (PPDB; Ganitkevitch et al., 2013) is an extensive semantic resource, consisting of a list of phrase pairs with (heuristic) confidence estimates.
no code implementations • 23 Sep 2015 • Kai-Wei Chang, Shyam Upadhyay, Ming-Wei Chang, Vivek Srikumar, Dan Roth
IllinoisSL is a Java library for learning structured prediction models.
no code implementations • TACL 2016 • Chen-Tse Tsai, Dan Roth
We also show that considering multiple knowledge bases together has an advantage over grounding concepts to each knowledge base individually.
1 code implementation • ACL 2016 • Shyam Upadhyay, Manaal Faruqui, Chris Dyer, Dan Roth
Despite interest in using cross-lingual knowledge to learn word embeddings for various tasks, a systematic comparison of the possible approaches is lacking in the literature.
no code implementations • 20 Apr 2016 • Daniel Khashabi, Tushar Khot, Ashish Sabharwal, Peter Clark, Oren Etzioni, Dan Roth
We propose a structured inference system for this task, formulated as an Integer Linear Program (ILP), that answers natural language questions using a semi-structured knowledge base derived from text, including questions requiring multi-step inference and a combination of multiple facts.
no code implementations • LREC 2016 • Mark Sammons, Christos Christodoulopoulos, Parisa Kordjamshidi, Daniel Khashabi, Vivek Srikumar, Dan Roth
We present EDISON, a Java library of feature generation functions used in a suite of state-of-the-art NLP tools, based on a set of generic NLP data structures.
no code implementations • ACL 2016 • Haoruo Peng, Dan Roth
Natural language understanding often requires deep semantic knowledge.
no code implementations • 30 Jul 2016 • Chenguang Wang, Yangqiu Song, Dan Roth, Ming Zhang, Jiawei Han
We provide three ways to specify the world knowledge to domains by resolving the ambiguity of the entities and their types, and represent the data with world knowledge as a heterogeneous information network.
no code implementations • EMNLP 2015 • Subhro Roy, Dan Roth
This paper presents a novel approach to automatically solving arithmetic word problems.
no code implementations • 14 Sep 2016 • Stephen Mayhew, Christos Christodoulopoulos, Dan Roth
We introduce a method for transliteration generation that can produce transliterations in every language.
no code implementations • 28 Sep 2016 • Subhro Roy, Shyam Upadhyay, Dan Roth
We introduce the problem of Equation Parsing -- given a sentence, identify noun phrases which represent variables, and generate the mathematical equation expressing the relation described in the sentence.
no code implementations • 13 Nov 2016 • Yangqiu Song, Stephen Mayhew, Dan Roth
We use a word-level dictionary to convert documents in a SWL to a large-Wikipedia language (LWLs), and then perform CLDDC based on the LWL's Wikipedia.
no code implementations • COLING 2016 • Chen-Tse Tsai, Dan Roth
The cross-lingual NER model is a language-independent model which can extract named entity mentions in the text of any language in Wikipedia.
no code implementations • COLING 2016 • Shyam Upadhyay, Nitish Gupta, Christos Christodoulopoulos, Dan Roth
Cross document event coreference (CDEC) is an important task that aims at aggregating event-related information across multiple documents.
1 code implementation • COLING 2016 • Parisa Kordjamshidi, Daniel Khashabi, Christos Christodoulopoulos, Bhargav Mangipudi, Sameer Singh, Dan Roth
We present a novel way for designing complex joint inference and learning models using Saul (Kordjamshidi et al., 2015), a recently-introduced declarative learning-based programming language (DeLBP).
no code implementations • 3 Dec 2016 • Subhro Roy, Dan Roth
Math word problems provide a natural abstraction to a range of natural language understanding problems that involve reasoning about quantities, such as interpreting election results, news about casualties, and the financial section of a newspaper.
no code implementations • EACL 2017 • Dan Roth, Vivek Srikumar
We will cover a range of topics, from the theoretical foundations of learning and inference with ILP models, to practical modeling guides, to software packages and applications. The goal of this tutorial is to introduce the computational framework to broader ACL community, motivate it as a generic framework for learning and inference in global NLP decision problems, present some of the key theoretical and practical issues involved and survey some of the existing applications of it as a way to promote further development of the framework and additional applications.
1 code implementation • WS 2017 • Rachel Wities, Vered Shwartz, Gabriel Stanovsky, Meni Adler, Ori Shapira, Shyam Upadhyay, Dan Roth, Eugenio Martinez Camara, Iryna Gurevych, Ido Dagan
We propose to move from Open Information Extraction (OIE) ahead to Open Knowledge Representation (OKR), aiming to represent information conveyed jointly in a set of texts in an open text-based manner.
no code implementations • 8 May 2017 • Yangqiu Song, Dan Roth
In this paper, we will discuss how to use the existing general-purpose world knowledge to enhance machine learning processes, by enriching the features or reducing the labeling work.
no code implementations • 25 Jul 2017 • Parisa Kordjamshidi, Sameer Singh, Daniel Khashabi, Christos Christodoulopoulos, Mark Summons, Saurabh Sinha, Dan Roth
In particular, we provide an initial prototype for a relational and graph traversal query language where queries are directly used as relational features for structured machine learning models.
1 code implementation • CONLL 2017 • Daniel Khashabi, Tushar Khot, Ashish Sabharwal, Dan Roth
Question answering (QA) systems are easily distracted by irrelevant or redundant words in questions, especially when faced with long or multi-sentence questions in difficult domains.
no code implementations • CONLL 2017 • Haoruo Peng, Snigdha Chaturvedi, Dan Roth
Understanding stories {--} sequences of events {--} is a crucial yet challenging natural language understanding task.
no code implementations • WS 2017 • Anjali Narayan-Chen, Colin Graber, Mayukh Das, Md. Rakibul Islam, Soham Dan, Sriraam Natarajan, Janardhan Rao Doppa, Julia Hockenmaier, Martha Palmer, Dan Roth
Agents that communicate back and forth with humans to help them execute non-linguistic tasks are a long sought goal of AI.
no code implementations • EMNLP 2017 • Stephen Mayhew, Chen-Tse Tsai, Dan Roth
Recent work in NLP has attempted to deal with low-resource languages but still assumed a resource level that is not present for most languages, e. g., the availability of Wikipedia in the target language.
no code implementations • EMNLP 2017 • Nitish Gupta, Sameer Singh, Dan Roth
For accurate entity linking, we need to capture various information aspects of an entity, such as its description in a KB, contexts in which it is mentioned, and structured knowledge.
no code implementations • EMNLP 2017 • Snigdha Chaturvedi, Haoruo Peng, Dan Roth
Automatic story comprehension is a fundamental challenge in Natural Language Understanding, and can enable computers to learn about social norms, human behavior and commonsense.
Ranked #13 on Question Answering on StoryCloze
no code implementations • CL 2017 • Alla Rozovskaya, Dan Roth, Mark Sammons
This article considers the problem of correcting errors made by English as a Second Language writers from a machine learning perspective, and addresses an important issue of developing an appropriate training paradigm for the task, one that accounts for error patterns of non-native writers using minimal supervision.
1 code implementation • TACL 2018 • Subhro Roy, Dan Roth
Solving such problems requires the understanding of several mathematical concepts such as dimensional analysis, subset relationships, etc.
1 code implementation • NAACL 2018 • Shyam Upadhyay, Yogarshi Vyas, Marine Carpuat, Dan Roth
We propose BISPARSE-DEP, a family of unsupervised approaches for cross-lingual hypernymy detection, which learns sparse, bilingual word embeddings based on dependency contexts.
no code implementations • NAACL 2018 • Qiang Ning, Hao Wu, Haoruo Peng, Dan Roth
We argue that this task would gain from the availability of a resource that provides prior knowledge in the form of the temporal order that events usually follow.
no code implementations • 18 Apr 2018 • Qiang Ning, Zhongzhi Yu, Chuchu Fan, Dan Roth
As a result, only a small number of documents are typically annotated, limiting the coverage of various lexical/semantic phenomena.
no code implementations • 19 Apr 2018 • Mayukh Das, Phillip Odom, Md. Rakibul Islam, Janardhan Rao, Doppa, Dan Roth, Sriraam Natarajan
Planning with preferences has been employed extensively to quickly generate high-quality plans.
no code implementations • ACL 2018 • Qiang Ning, Hao Wu, Dan Roth
Existing temporal relation (TempRel) annotation schemes often have low inter-annotator agreements (IAA) even between experts, suggesting that the current annotation task needs a better definition.
1 code implementation • ACL 2018 • Wenpeng Yin, Hinrich Schütze, Dan Roth
This work deals with SciTail, a natural entailment challenge derived from a multi-choice question answering problem.
1 code implementation • LREC 2018 • Daniel Khashabi, Mark Sammons, Ben Zhou, Tom Redman, Christos Christodoulopoulos, Vivek Srikumar, Nicholas Rizzolo, Lev Ratinov, Guanheng Luo, Quang Do, Chen-Tse Tsai, Subhro Roy, Stephen Mayhew, Zhili Feng, John Wieting, Xiaodong Yu, Yangqiu Song, Shashank Gupta, Shyam Upadhyay, Naveen Arivazhagan, Qiang Ning, Shaoshi Ling, Dan Roth
no code implementations • SEMEVAL 2018 • Abhijit Mahabal, Dan Roth, Sid Mittal
Words are polysemous and multi-faceted, with many shades of meanings.
no code implementations • NAACL 2018 • Daniel Khashabi, Snigdha Chaturvedi, Michael Roth, Shyam Upadhyay, Dan Roth
We present a reading comprehension challenge in which questions can only be answered by taking into account information from multiple sentences.
no code implementations • SEMEVAL 2018 • Qiang Ning, Zhongzhi Yu, Chuchu Fan, Dan Roth
As a result, only a small number of documents are typically annotated, limiting the coverage of various lexical/semantic phenomena.
no code implementations • NAACL 2018 • Snigdha Chaturvedi, Shashank Srivastava, Dan Roth
People can identify correspondences between narratives in everyday life.
no code implementations • SEMEVAL 2018 • Wenpeng Yin, Dan Roth
Existing methods of hypernymy detection mainly rely on statistics over a big corpus, either mining some co-occurring patterns like "animals such as cats" or embedding words of interest into context-aware vectors.
1 code implementation • ACL 2018 • Stephen Mayhew, Dan Roth
We present a new web-based interface, TALEN, designed for named entity annotation in low-resource settings where the annotators do not speak the language.
no code implementations • ACL 2018 • Avi Sil, Heng Ji, Dan Roth, Silviu-Petru Cucerzan
We will then proceed to Cross-lingual EL and discuss methods that work across languages.
1 code implementation • ACL 2018 • Daniel Deutsch, John Hewitt, Dan Roth
Modeling derivational morphology to generate words with particular semantics is useful in many text generation tasks, such as machine translation or abstractive question answering.
1 code implementation • COLING 2018 • Lori Moon, Christos Christodoulopoulos, Cynthia Fisher, S. Franco, ra, Dan Roth
Inter-annotator agreement is given separately for prepositions and verbs, and for adult speech and child speech.
1 code implementation • EMNLP 2018 • Wenpeng Yin, Dan Roth
We develop TwoWingOS (two-wing optimization strategy), a system that, while identifying appropriate evidence for a claim, also determines whether or not the claim is supported by the evidence.
no code implementations • EMNLP 2018 • Xiaodong Yu, Stephen Mayhew, Mark Sammons, Dan Roth
Character-level patterns have been widely used as features in English Named Entity Recognition (NER) systems.
Multilingual Named Entity Recognition named-entity-recognition +2
1 code implementation • EMNLP 2018 • Shyam Upadhyay, Jordan Kodner, Dan Roth
Generating the English transliteration of a name written in a foreign script is an important and challenging step in multilingual knowledge acquisition and information extraction.
1 code implementation • EMNLP 2018 • Shyam Upadhyay, Nitish Gupta, Dan Roth
This enables our approach to: (a) augment the limited supervision in the target language with additional supervision from a high-resource language (like English), and (b) train a single entity linking model for multiple languages, improving upon individually trained models for each language.
no code implementations • 26 Oct 2018 • Oshin Agarwal, Sanjay Subramanian, Ani Nenkova, Dan Roth
Here, we evaluate two state of the art coreference resolution systems on the subtask of Named Person Coreference, in which we are interested in identifying a person mentioned by name, along with all other mentions of the person, by pronoun or generic noun phrase.
no code implementations • EMNLP 2018 • Qiang Ning, Ben Zhou, Zhili Feng, Haoruo Peng, Dan Roth
Automatic extraction of temporal information is important for natural language understanding.
no code implementations • 13 Nov 2018 • Mrinmaya Sachan, Kumar Avinava Dubey, Eduard H. Hovy, Tom M. Mitchell, Dan Roth, Eric P. Xing
At the same time, these help the readers pick up the structure of the discourse and comprehend the conveyed information.
no code implementations • NeurIPS 2018 • Mrinmaya Sachan, Kumar Avinava Dubey, Tom M. Mitchell, Dan Roth, Eric P. Xing
Finally, we also show how Nuts&Bolts can be used to achieve improvements on a relation extraction task and on the end task of answering Newtonian physics problems.
no code implementations • 8 Jan 2019 • Daniel Khashabi, Erfan Sadeqi Azer, Tushar Khot, Ashish Sabharwal, Dan Roth
The idea is to consider two interrelated spaces: a conceptual meaning space that is unambiguous and complete but hidden, and a linguistic space that captures a noisy grounding of the meaning space in the words of a language---the level at which all systems, whether neural or symbolic, operate.
1 code implementation • CONLL 2019 • Hai Wang, Dian Yu, Kai Sun, Jianshu Chen, Dong Yu, David Mcallester, Dan Roth
Remarkable success has been achieved in the last few years on some limited machine reading comprehension (MRC) tasks.
no code implementations • TACL 2019 • Alla Rozovskaya, Dan Roth
Although impressive results have recently been achieved for grammar error correction of non-native English writing, these results are limited to domains where plentiful training data are available.
no code implementations • IJCNLP 2019 • Stephen Mayhew, Tatiana Tsygankova, Dan Roth
While prior work and first impressions might suggest training a caseless model, or using a truecaser at test time, we show that the most effective strategy is a concatenation of cased and lowercased training data, producing a single model with high performance on both cased and uncased text.
1 code implementation • NAACL 2019 • Sihao Chen, Daniel Khashabi, Wenpeng Yin, Chris Callison-Burch, Dan Roth
Inherently, this is a natural language understanding task, and we propose to address it as such.
no code implementations • WS 2019 • Oshin Agarwal, Sanjay Subramanian, Ani Nenkova, Dan Roth
It is therefore important that coreference resolution systems are able to link these different types of mentions to the correct entity name.
1 code implementation • ACL 2019 • Yanai Elazar, Abhijit Mahabal, Deepak Ramachandran, Tania Bedrax-Weiss, Dan Roth
Most current NLP systems have little knowledge about quantitative attributes of objects and events.
1 code implementation • 8 Jun 2019 • Sihao Chen, Daniel Khashabi, Wenpeng Yin, Chris Callison-Burch, Dan Roth
Inherently, this is a natural language understanding task, and we propose to address it as such.
1 code implementation • 9 Jun 2019 • Daniel Khashabi, Tushar Khot, Ashish Sabharwal, Dan Roth
We propose a novel method for exploiting the semantic structure of text to answer multiple-choice questions.
1 code implementation • ACL 2019 • Sihao Chen, Daniel Khashabi, Chris Callison-Burch, Dan Roth
This work presents PerspectroScope, a web-based system which lets users query a discussion-worthy natural language claim, and extract and visualize various perspectives in support or against the claim, along with evidence supporting each perspective.
Natural Language Inference Natural Language Understanding +1
no code implementations • 12 Jun 2019 • Qiang Ning, Ben Zhou, Zhili Feng, Haoruo Peng, Dan Roth
Automatic extraction of temporal information in text is an important component of natural language understanding.
no code implementations • NAACL 2019 • Qiang Ning, Hangfeng He, Chuchu Fan, Dan Roth
For many structured learning tasks, the data annotation process is complex and costly.
no code implementations • EMNLP 2017 • Qiang Ning, Zhili Feng, Dan Roth
Identifying temporal relations between events is an essential step towards natural language understanding.
Ranked #1 on Temporal Information Extraction on TempEval-3
no code implementations • ACL 2018 • Qiang Ning, Zhili Feng, Hao Wu, Dan Roth
Understanding temporal and causal relations between events is a fundamental natural language understanding task.
no code implementations • 18 Jun 2019 • Parisa Kordjamshidi, Dan Roth, Kristian Kersting
Data-driven approaches are becoming more common as problem-solving techniques in many areas of research and industry.
no code implementations • ACL 2019 • Yi Zhang, Zachary Ives, Dan Roth
This paper develops a general framework for estimating the trustworthiness of information sources in an environment where multiple sources provide claims and supporting evidence, and each claim can potentially be produced by multiple sources.
1 code implementation • EMNLP 2018 • Ben Zhou, Daniel Khashabi, Chen-Tse Tsai, Dan Roth
We evaluate our system on a broad range of datasets, including standard fine-grained and coarse-grained entity typing datasets, and also a dataset in the biological domain.
no code implementations • HLT 2015 • Haoruo Peng, Daniel Khashabi, Dan Roth
Coreference resolution is a key problem in natural language understanding that still escapes reliable solutions.
no code implementations • WS 2019 • Tatiana Tsygankova, Stephen Mayhew, Dan Roth
This paper describes the Cognitive Computation (CogComp) Group{'}s submissions to the multilingual named entity recognition shared task at the Balto-Slavic Natural Language Processing (BSNLP) Workshop.
Multilingual Named Entity Recognition named-entity-recognition +2
no code implementations • SEMEVAL 2019 • Sanjay Subramanian, Dan Roth
In order for coreference resolution systems to be useful in practice, they must be able to generalize to new text.
4 code implementations • IJCNLP 2019 • Wenpeng Yin, Jamaal Hay, Dan Roth
0Shot-TC aims to associate an appropriate label with a piece of text, irrespective of the text domain and the aspect (e. g., topic, emotion, event, etc.)
no code implementations • IJCNLP 2019 • Qiang Ning, Sanjay Subramanian, Dan Roth
Determining temporal relations (e. g., before or after) between events has been a challenging natural language understanding task, partly due to the difficulty to generate large amounts of high-quality training data.
1 code implementation • ACL 2020 • Hangfeng He, Qiang Ning, Dan Roth
Question-answering (QA) data often encodes essential information in many facets.
1 code implementation • 6 Sep 2019 • Ben Zhou, Daniel Khashabi, Qiang Ning, Dan Roth
Understanding time is crucial for understanding events expressed in natural language.
no code implementations • CONLL 2019 • Stephen Mayhew, Snigdha Chaturvedi, Chen-Tse Tsai, Dan Roth
Supervised machine learning assumes the availability of fully-labeled data, but in many cases, such as low-resource languages, the only data available is partially annotated.
no code implementations • IJCNLP 2019 • Ben Zhou, Daniel Khashabi, Qiang Ning, Dan Roth
Understanding time is crucial for understanding events expressed in natural language.
no code implementations • CONLL 2019 • Haoruo Peng, Qiang Ning, Dan Roth
Story understanding requires developing expectations of what events come next in text.
no code implementations • CONLL 2019 • Daniel Deutsch, Shyam Upadhyay, Dan Roth
We experimentally show the benefits of our algorithm on constituency parsing and semantic role labeling.
no code implementations • IJCNLP 2019 • Daniel Deutsch, Dan Roth
A key challenge in topic-focused summarization is determining what information should be included in the summary, a problem known as content selection.
1 code implementation • ACL 2020 • Erfan Sadeqi Azer, Daniel Khashabi, Ashish Sabharwal, Dan Roth
Empirical research in Natural Language Processing (NLP) has adopted a narrow set of principles for assessing hypotheses, relying mainly on p-value computation, which suffers from several known issues.
no code implementations • CL 2019 • Mrinmaya Sachan, Avinava Dubey, Eduard H. Hovy, Tom M. Mitchell, Dan Roth, Eric P. Xing
At the same time, these help the readers pick up the structure of the discourse and comprehend the conveyed information.
2 code implementations • ICLR 2020 • Nitish Gupta, Kevin Lin, Dan Roth, Sameer Singh, Matt Gardner
Answering compositional questions that require multiple steps of reasoning against text is challenging, especially when they involve discrete, symbolic operations.
no code implementations • 15 Dec 2019 • Stephen Mayhew, Nitish Gupta, Dan Roth
Although modern named entity recognition (NER) systems show impressive performance on standard datasets, they perform poorly when presented with noisy data.
Ranked #10 on Named Entity Recognition (NER) on WNUT 2017
no code implementations • ICLR 2020 • Karthikeyan K, Zihan Wang, Stephen Mayhew, Dan Roth
Recent work has exhibited the surprising cross-lingual abilities of multilingual BERT (M-BERT) -- surprising since it is trained without any cross-lingual objective and with no aligned data.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Zihan Wang, Karthikeyan K, Stephen Mayhew, Dan Roth
Multilingual BERT (M-BERT) has been a huge success in both supervised and zero-shot cross-lingual transfer learning.
no code implementations • EMNLP 2020 • Qiang Ning, Hao Wu, Rujun Han, Nanyun Peng, Matt Gardner, Dan Roth
A critical part of reading is being able to understand the temporal relationships between events described in a passage of text, even when those relationships are not explicitly stated.
Ranked #2 on Question Answering on Torque
1 code implementation • EACL 2021 • Muhao Chen, Weijia Shi, Ben Zhou, Dan Roth
Much research effort has been put to multilingual knowledge graph (KG) embedding methods to address the entity alignment task, which seeks to match entities in different languagespecific KGs that refer to the same real-world object.
Ranked #19 on Entity Alignment on DBP15k zh-en
1 code implementation • 1 May 2020 • Hongming Zhang, Daniel Khashabi, Yangqiu Song, Dan Roth
Commonsense knowledge acquisition is a key problem for artificial intelligence.
1 code implementation • EMNLP 2020 • Xingyu Fu, Weijia Shi, Xiaodong Yu, Zian Zhao, Dan Roth
Cross-lingual Entity Linking (XEL), the problem of grounding mentions of entities in a foreign language text into an English knowledge base such as Wikipedia, has seen a lot of research in recent years, with a range of promising techniques.
no code implementations • ACL 2020 • Ben Zhou, Qiang Ning, Daniel Khashabi, Dan Roth
Temporal common sense (e. g., duration and frequency of events) is crucial for understanding natural language.
no code implementations • 17 May 2020 • Ansel MacLaughlin, Tao Chen, Burcu Karagol Ayan, Dan Roth
Our experiments confirm the strong performance of BERT-based methods on this task, which outperform bag-of-words and neural ranking baselines by more than 30% relative across all ranking metrics.
no code implementations • NAACL 2019 • Abhijit Mahabal, Jason Baldridge, Burcu Karagol Ayan, Vincent Perot, Dan Roth
Training data for text classification is often limited in practice, especially for applications with many output classes or involving many related classification problems.
no code implementations • 25 May 2020 • Dan Roth
Machine Learning and Inference methods have become ubiquitous in our attempt to induce more abstract representations of natural language text, visual scenes, and other messy, naturally occurring data, and support decisions that depend on it.
2 code implementations • EMNLP 2021 • Hangfeng He, Mingyuan Zhang, Qiang Ning, Dan Roth
Real-world applications often require improved models by leveraging a range of cheap incidental supervision signals.
no code implementations • NeurIPS 2020 • Kaifu Wang, Qiang Ning, Dan Roth
Learning from indirect supervision signals is important in real-world AI applications when, often, gold labels are missing or too costly.
no code implementations • 17 Jun 2020 • Tatiana Tsygankova, Francesca Marini, Stephen Mayhew, Dan Roth
In low-resource natural language processing (NLP), the key problems are a lack of target language training data, and a lack of native speakers to create it.
Low Resource Named Entity Recognition named-entity-recognition +2
no code implementations • ACL 2020 • Yi Zhang, Zachary Ives, Dan Roth
In an era where generating content and publishing it is so easy, we are bombarded with information and are exposed to all kinds of claims, some of which do not always rank high on the truth scale.
no code implementations • ACL 2020 • Maarten Sap, Vered Shwartz, Antoine Bosselut, Yejin Choi, Dan Roth
We organize this tutorial to provide researchers with the critical foundations and recent advances in commonsense representation and reasoning, in the hopes of casting a brighter light on this promising area of future research.
1 code implementation • EMNLP (NLPOSS) 2020 • Daniel Deutsch, Dan Roth
We present SacreROUGE, an open-source library for using and developing summarization evaluation metrics.
no code implementations • LREC 2020 • Soham Dan, Hangfeng He, Dan Roth
Recognizing spatial relations and reasoning about them is essential in multiple applications including navigation, direction giving and human-computer interaction in general.
no code implementations • LREC 2020 • Soham Dan, Parisa Kordjamshidi, Julia Bonn, Archna Bhatia, Jon Cai, Martha Palmer, Dan Roth
To exhibit the applicability of our representation scheme, we annotate text taken from diverse datasets and show how we extend the capabilities of existing spatial representation languages with the fine-grained decomposition of semantics and blend it seamlessly with AMRs of sentences and discourse representations as a whole.
1 code implementation • 24 Sep 2020 • Semantic Machines, Jacob Andreas, John Bufe, David Burkett, Charles Chen, Josh Clausman, Jean Crawford, Kate Crim, Jordan DeLoach, Leah Dorner, Jason Eisner, Hao Fang, Alan Guo, David Hall, Kristin Hayes, Kellie Hill, Diana Ho, Wendy Iwaszuk, Smriti Jha, Dan Klein, Jayant Krishnamurthy, Theo Lanman, Percy Liang, Christopher H Lin, Ilya Lintsbakh, Andy McGovern, Aleksandr Nisnevich, Adam Pauls, Dmitrij Petters, Brent Read, Dan Roth, Subhro Roy, Jesse Rusak, Beth Short, Div Slomin, Ben Snyder, Stephon Striplin, Yu Su, Zachary Tellman, Sam Thomson, Andrei Vorobev, Izabela Witoszko, Jason Wolfe, Abby Wray, Yuchen Zhang, Alexander Zotov
We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph.
2 code implementations • 28 Sep 2020 • Fangyu Liu, Muhao Chen, Dan Roth, Nigel Collier
This work studies the use of visual semantic representations to align entities in heterogeneous knowledge graphs (KGs).
Ranked #3 on Multi-modal Entity Alignment on UMVM-oea-d-w-v1 (using extra training data)
2 code implementations • 1 Oct 2020 • Daniel Deutsch, Tania Bedrax-Weiss, Dan Roth
A desirable property of a reference-based evaluation metric that measures the content quality of a summary is that it should estimate how much information that summary has in common with a reference.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Zi Lin, Jeremiah Zhe Liu, Zi Yang, Nan Hua, Dan Roth
Traditional (unstructured) pruning methods for a Transformer model focus on regularizing the individual weights by penalizing them toward zero.
no code implementations • 7 Oct 2020 • Annie Louis, Dan Roth, Filip Radlinski
We revisit a pragmatic inference problem in dialog: understanding indirect responses to questions.
no code implementations • EMNLP (BlackboxNLP) 2020 • Xikun Zhang, Deepak Ramachandran, Ian Tenney, Yanai Elazar, Dan Roth
Pretrained Language Models (LMs) have been shown to possess significant linguistic, common sense, and factual knowledge.
no code implementations • EMNLP 2020 • Haoyu Wang, Muhao Chen, Hongming Zhang, Dan Roth
Understanding natural language involves recognizing how multiple event mentions structurally and temporally interact with each other.
no code implementations • 13 Oct 2020 • Muhao Chen, Hongming Zhang, Haoyu Wang, Dan Roth
This paper studies a new cognitively motivated semantic typing task, multi-axis event process typing, that, given an event process, attempts to infer free-form type labels describing (i) the type of action made by the process and (ii) the type of object the process seeks to affect.
no code implementations • EMNLP 2020 • Hongming Zhang, Muhao Chen, Haoyu Wang, Yangqiu Song, Dan Roth
Computational and cognitive studies of event understanding suggest that identifying, comprehending, and predicting events depend on having structured representations of a sequence of events and on conceptualizing (abstracting) its components into (soft) event categories.
1 code implementation • 23 Oct 2020 • Daniel Deutsch, Dan Roth
Reference-based metrics such as ROUGE or BERTScore evaluate the content quality of a summary by comparing the summary to a reference.
no code implementations • *SEM (NAACL) 2022 • Xiaodong Yu, Wenpeng Yin, Dan Roth
Natural Language Processing tasks such as resolving the coreference of events require understanding the relations between two text snippets.
no code implementations • NAACL 2021 • Ben Zhou, Kyle Richardson, Qiang Ning, Tushar Khot, Ashish Sabharwal, Dan Roth
We propose TRACIE, a novel temporal reasoning dataset that evaluates the degree to which systems understand implicit events -- events that are not mentioned explicitly in natural language text but can be inferred from it.
no code implementations • CONLL 2020 • Muhao Chen, Hongming Zhang, Haoyu Wang, Dan Roth
This paper studies a new cognitively motivated semantic typing task, multi-axis event process typing, that, given anevent process, attempts to infer free-form typelabels describing (i) the type of action made bythe process and (ii) the type of object the pro-cess seeks to affect.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Krunal Shah, Nitish Gupta, Dan Roth
The recent success of machine learning systems on various QA datasets could be interpreted as a significant improvement in models' language understanding abilities.
no code implementations • COLING 2020 • Disha Jindal, Daniel Deutsch, Dan Roth
Identifying the key events in a document is critical to holistically understanding its important information.
1 code implementation • COLING 2020 • Ayal Klein, Jonathan Mamou, Valentina Pyatkin, Daniela Stepanov, Hangfeng He, Dan Roth, Luke Zettlemoyer, Ido Dagan
We propose a new semantic scheme for capturing predicate-argument relations for nominalizations, termed QANom.
1 code implementation • 13 Dec 2020 • Hongming Zhang, Yintong Huo, Xinran Zhao, Yangqiu Song, Dan Roth
Compared with pure text-based approaches, learning causality from the visual signal has the following advantages: (1) Causality knowledge belongs to the commonsense knowledge, which is rarely expressed in the text but rich in videos; (2) Most events in the video are naturally time-ordered, which provides a rich resource for us to mine causality knowledge from; (3) All the objects in the video can be used as context to study the contextual property of causal relations.
no code implementations • 30 Dec 2020 • Hongming Zhang, Haoyu Wang, Dan Roth
Rather than relying on annotated data, our model matches the semantics of identified events with those of event type labels.
1 code implementation • ACL 2021 • Mingzhu Wu, Nafise Sadat Moosavi, Dan Roth, Iryna Gurevych
We propose a methodology for creating MRC datasets that better reflect the challenges of coreference reasoning and use it to create a sample evaluation set.
no code implementations • 1 Jan 2021 • Hangfeng He, Mingyuan Zhang, Qiang Ning, Dan Roth
Real-world applications often require making use of {\em a range of incidental supervision signals}.
1 code implementation • 6 Jan 2021 • Mor Geva, Daniel Khashabi, Elad Segal, Tushar Khot, Dan Roth, Jonathan Berant
A key limitation in current datasets for multi-hop reasoning is that the required steps for answering the question are mentioned in it explicitly.
1 code implementation • 31 Mar 2021 • Daniel Deutsch, Rotem Dror, Dan Roth
After evaluating which of the proposed methods is most appropriate for summarization through two simulation experiments, we analyze the results of applying these methods to several different automatic evaluation metrics across three sets of human annotations.
no code implementations • EACL 2021 • Alla Rozovskaya, Dan Roth
Standard evaluations of Grammatical Error Correction (GEC) systems make use of a fixed reference text generated relative to the original text; they show, even when using multiple references, that we have a long way to go.
no code implementations • EMNLP 2021 • Nitish Gupta, Sameer Singh, Matt Gardner, Dan Roth
Such an objective does not require external supervision for the values of the latent output, or even the end task, yet provides an additional training signal to that provided by individual training examples themselves.
1 code implementation • 16 Apr 2021 • Rujun Han, I-Hung Hsu, Jiao Sun, Julia Baylon, Qiang Ning, Dan Roth, Nanyun Peng
While these tasks partially evaluate machines' ability of narrative understanding, human-like reading comprehension requires the capability to process event-based information beyond arguments and temporal reasoning.
1 code implementation • 16 Apr 2021 • Nafise Sadat Moosavi, Andreas Rücklé, Dan Roth, Iryna Gurevych
In this paper, we introduce SciGen, a new challenge dataset for the task of reasoning-aware data-to-text generation consisting of tables from scientific articles and their corresponding descriptions.
no code implementations • EMNLP 2021 • Yanai Elazar, Hongming Zhang, Yoav Goldberg, Dan Roth
To support this claim, we first show that the current evaluation method of WS is sub-optimal and propose a modification that uses twin sentences for evaluation.
Ranked #24 on Coreference Resolution on Winograd Schema Challenge
no code implementations • NAACL 2021 • Sihao Chen, Fan Zhang, Kazoo Sone, Dan Roth
Despite significant progress in neural abstractive summarization, recent studies have shown that the current models are prone to generating summaries that are unfaithful to the original context.
no code implementations • 26 Apr 2021 • Celine Lee, Justin Gottschlich, Dan Roth
With the growth of natural language processing techniques and demand for improved software engineering efficiency, there is an emerging interest in translating intention from human languages to programming languages.
1 code implementation • ICLR 2022 • Shuxiao Chen, Koby Crammer, Hangfeng He, Dan Roth, Weijie J. Su
In this paper, we introduce Target-Aware Weighted Training (TAWT), a weighted training algorithm for cross-task learning based on minimizing a representation-based task distance between the source and target tasks.
no code implementations • NAACL 2021 • Soham Dan, Michael Zhou, Dan Roth
Understanding and executing natural language instructions in a grounded domain is one of the hallmarks of artificial intelligence.
1 code implementation • NAACL 2021 • Yi Zhang, Sujay Kumar Jauhar, Julia Kiseleva, Ryen White, Dan Roth
Both components of our graph induction solution are evaluated in experiments, demonstrating that our models outperform a state-of-the-art text generator significantly.
1 code implementation • NAACL 2021 • Haoyang Wen, Yanru Qu, Heng Ji, Qiang Ning, Jiawei Han, Avi Sil, Hanghang Tong, Dan Roth
Grounding events into a precise timeline is important for natural language understanding but has received limited attention in recent work.
1 code implementation • NAACL 2021 • Haoyang Wen, Ying Lin, Tuan Lai, Xiaoman Pan, Sha Li, Xudong Lin, Ben Zhou, Manling Li, Haoyu Wang, Hongming Zhang, Xiaodong Yu, Alexander Dong, Zhenhailong Wang, Yi Fung, Piyush Mishra, Qing Lyu, D{\'\i}dac Sur{\'\i}s, Brian Chen, Susan Windisch Brown, Martha Palmer, Chris Callison-Burch, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Heng Ji
We present a new information extraction system that can automatically construct temporal event graphs from a collection of news documents from multiple sources, multiple languages (English and Spanish for our experiment), and multiple data modalities (speech, text, image and video).
1 code implementation • NAACL 2021 • Siyi Liu, Sihao Chen, Xander Uyttendaele, Dan Roth
We propose MultiOpEd, an open-domain news editorial corpus that supports various tasks pertaining to the argumentation structure in news editorials, focusing on automatic perspective discovery.
no code implementations • ACL 2021 • Yi Zhang, Zachary Ives, Dan Roth
We experiment with a newly created evaluation dataset, Politi-Prov, based on fact-checking articles from \url{www. politifact. com}; our experimental results show that our solution leads to a significant improvement over baselines.
no code implementations • ACL 2021 • Muhao Chen, Hongming Zhang, Qiang Ning, Manling Li, Heng Ji, Kathleen McKeown, Dan Roth
This tutorial targets researchers and practitioners who are interested in AI technologies that help machines understand natural language text, particularly real-world events described in the text.
no code implementations • ACL 2021 • Qing Lyu, Hongming Zhang, Elior Sulem, Dan Roth
Event extraction has long been a challenging task, addressed mostly with supervised methods that require expensive annotation and are not extensible to new event ontologies.
no code implementations • EMNLP 2021 • Haoyu Wang, Hongming Zhang, Muhao Chen, Dan Roth
The task of subevent detection aims to resolve this granularity issue, recognizing the membership of multi-granular events in event complexes.
no code implementations • 1 Nov 2021 • Bonan Min, Hayley Ross, Elior Sulem, Amir Pouran Ben Veyseh, Thien Huu Nguyen, Oscar Sainz, Eneko Agirre, Ilana Heinz, Dan Roth
Large, pre-trained transformer-based language models such as BERT have drastically changed the Natural Language Processing (NLP) field.
no code implementations • 15 Nov 2021 • Daniel Deutsch, Dan Roth
In this work, we propose a method for incorporating question-answering (QA) signals into a summarization model.
1 code implementation • Findings (NAACL) 2022 • Sihao Chen, Siyi Liu, Xander Uyttendaele, Yi Zhang, William Bruno, Dan Roth
Naturally, identifying such responses within a document is a natural language understanding task.
1 code implementation • 15 Dec 2021 • Xiaodong Yu, Wenpeng Yin, Nitish Gupta, Dan Roth
Third, we retrain and evaluate two state-of-the-art (SOTA) entity linking models, showing the challenges of event linking, and we propose an event-specific linking system EVELINK to set a competitive result for the new task.
2 code implementations • 28 Jan 2022 • Uri Alon, Frank F. Xu, Junxian He, Sudipta Sengupta, Dan Roth, Graham Neubig
Retrieval-based language models (R-LM) model the probability of natural language text by combining a standard language model (LM) with examples retrieved from an external datastore at test time.
1 code implementation • 31 Jan 2022 • Jiayao Zhang, Hongming Zhang, Weijie J. Su, Dan Roth
Commonsense causality reasoning (CCR) aims at identifying plausible causes and effects in natural language descriptions that are deemed reasonable by an average person.
no code implementations • 20 Feb 2022 • Soham Dan, Osbert Bastani, Dan Roth
Currently, deep neural networks struggle to generalize robustly to such shifts in the data distribution.
1 code implementation • 1 Mar 2022 • Xingyu Fu, Ben Zhou, Ishaan Preetam Chandratreya, Carl Vondrick, Dan Roth
For example, in Figure 1, we can find a way to identify the news articles related to the picture through segment-wise understandings of the signs, the buildings, the crowds, and more.
1 code implementation • CVPR 2022 • Georgios Georgakis, Karl Schmeckpeper, Karan Wanchoo, Soham Dan, Eleni Miltsakaki, Dan Roth, Kostas Daniilidis
We consider the problem of Vision-and-Language Navigation (VLN).
1 code implementation • Findings (ACL) 2022 • Jie Ma, Miguel Ballesteros, Srikanth Doss, Rishita Anubhai, Sunil Mallya, Yaser Al-Onaizan, Dan Roth
We study the problem of few shot learning for named entity recognition.
2 code implementations • ACL 2022 • Zheng Li, Zijian Wang, Ming Tan, Ramesh Nallapati, Parminder Bhatia, Andrew Arnold, Bing Xiang, Dan Roth
Empirical analyses show that, despite the challenging nature of generative tasks, we were able to achieve a 16. 5x model footprint compression ratio with little performance drop relative to the full-precision counterparts on multiple summarization and QA datasets.
1 code implementation • ACL 2022 • Aaron Mueller, Jason Krone, Salvatore Romeo, Saab Mansour, Elman Mansimov, Yi Zhang, Dan Roth
Label semantic aware systems have leveraged this information for improved text classification performance during fine-tuning and prediction.
no code implementations • Findings (ACL) 2022 • Daniel Deutsch, Dan Roth
Question answering-based summarization evaluation metrics must automatically determine whether the QA model's prediction is correct or not, a task known as answer verification.
no code implementations • NAACL 2022 • Daniel Deutsch, Rotem Dror, Dan Roth
How reliably an automatic summarization evaluation metric replicates human judgments of summary quality is quantified by system-level correlations.
1 code implementation • 29 Apr 2022 • Daniel Deutsch, Dan Roth
We introduce Repro, an open-source library which aims at improving the reproducibility and usability of research code.