Search Results for author:
Found 105 papers, 35 papers with code
Intrinsic Evaluation of Summarization Datasets
High quality data forms the bedrock for building meaningful statistical models in NLP.
SUMSUM@FNS-2020 Shared Task
This paper describes the SUMSUM systems submitted to the Financial Narrative Summarization Shared Task (FNS-2020).
Question Generation using a Scratchpad Encoder
In this paper we introduce the Scratchpad Encoder, a novel addition to the sequence to sequence (seq2seq) framework and explore its effectiveness in generating natural language questions from a given logical form.
BeSt: The Belief and Sentiment Corpus
We present the BeSt corpus, which records cognitive state: who believes what (i. e., factuality), and who has what sentiment towards what.
WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild
The increasing availability of real-world conversation data offers exciting opportunities for researchers to study user-chatbot interactions.
WildHallucinations: Evaluating Long-form Factuality in LLMs with Real-World Entity Queries
While hallucinations of large language models (LLMs) prevail as a major challenge, existing evaluation benchmarks on factuality do not cover the diverse domains of knowledge that the real-world users of LLMs seek information about.
I Could've Asked That: Reformulating Unanswerable Questions
We curate CouldAsk, an evaluation benchmark composed of existing and new datasets for document-grounded question answering, specifically designed to study reformulating unanswerable questions.
Corpus Poisoning via Approximate Greedy Gradient Descent
Dense retrievers are widely used in information retrieval and have also been successfully extended to other knowledge intensive areas such as language models, e. g., Retrieval-Augmented Generation (RAG) systems.
WildChat: 1M ChatGPT Interaction Logs in the Wild
In addition to timestamped chat transcripts, we enrich the dataset with demographic data, including state, country, and hashed IP addresses, alongside request headers.
Adapting Fake News Detection to the Era of Large Language Models
With the proliferation of both human-written and machine-generated real and fake news, robustly and effectively discerning the veracity of news articles has become an intricate challenge.
Probing Representations for Document-level Event Extraction
This work is the first to apply the probing paradigm to representations learned for document-level information extraction (IE).
Policy-Gradient Training of Language Models for Ranking
Text retrieval plays a crucial role in incorporating factual knowledge for decision making into language processing pipelines, ranging from chat-based web search to question answering systems.
Abductive Commonsense Reasoning Exploiting Mutually Exclusive Explanations
Instead of using direct supervision, this work proposes an approach for abductive commonsense reasoning that exploits the fact that only a subset of explanations is correct for a given context.
HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision
Explainable multi-hop question answering (QA) not only predicts answers but also identifies rationales, i. e. subsets of input sentences used to derive the answers.
Fashionpedia-Ads: Do Your Favorite Advertisements Reveal Your Fashion Taste?
Does ads from other domains infer their fashion taste as well?
Fashionpedia-Taste: A Dataset towards Explaining Human Fashion Taste
Existing fashion datasets do not consider the multi-facts that cause a consumer to like or dislike a fashion image.
Automatic Error Analysis for Document-level Information Extraction
Document-level information extraction (IE) tasks have recently begun to be revisited in earnest using the end-to-end neural network techniques that have been successful on their sentence-level IE counterparts.
Compositional Task-Oriented Parsing as Abstractive Question Answering
Task-oriented parsing (TOP) aims to convert natural language into machine-readable representations of specific tasks, such as setting an alarm.
Visual Prompt Tuning
The current modus operandi in adapting pre-trained models involves updating all the backbone parameters, ie, full fine-tuning.
Ranked #2 on
Prompt Engineering
on ImageNet-21k
Rethinking Nearest Neighbors for Visual Classification
In this paper, we investigate $k$-Nearest-Neighbor (k-NN) classifiers, a classical model-free learning method from the pre-deep learning era, as an augmentation to modern neural network based approaches.
Learning to Adapt to Semantic Shift
These models outperform both previous work and static models under both \emph{static} and \emph{continual} semantic shifts, suggesting that ``learning to adapt'' is a useful capability for models and agents in a changing world.
When in Doubt: Improving Classification Performance with Alternating Normalization
We introduce Classification with Alternating Normalization (CAN), a non-parametric post-processing step for classification.
Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive Summarization
Despite recent progress in abstractive summarization, systems still suffer from faithfulness errors.
Template Filling with Generative Transformers
Template filling is generally tackled by a pipeline of two separate supervised systems {--} one for role-filler extraction and another for template/event recognition.
Exploring Visual Engagement Signals for Representation Learning
Visual engagement in social media platforms comprises interactions with photo posts including comments, shares, and likes.
Self-Teaching Machines to Read and Comprehend with Large-Scale Multi-Subject Question-Answering Data
In spite of much recent research in the area, it is still unclear whether subject-area question-answering data is useful for machine reading comprehension (MRC) tasks.
Leveraging Structured Metadata for Improving Question Answering on the Web
We show that leveraging metadata information from web pages can improve the performance of models for answer passage selection/reranking.
Intentonomy: a Dataset and Study towards Human Intent Understanding
Based on our findings, we conduct further study to quantify the effect of attending to object and context classes as well as textual information in the form of hashtags when training an intent classifier.
Improving Event Duration Prediction via Time-aware Pre-training
End-to-end models in NLP rarely encode external world knowledge about length of time.
Adding Chit-Chat to Enhance Task-Oriented Dialogues
Existing dialogue corpora and models are typically designed under two disjoint motives: while task-oriented systems focus on achieving functional goals (e. g., booking hotels), open-domain chatbots aim at making socially engaging conversations.
WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization
As a set of baselines for further studies, we evaluate the performance of existing cross-lingual abstractive summarization methods on our dataset.
Abstractive Text Summarization
Cross-Lingual Abstractive Summarization
+2
Exploring the Role of Argument Structure in Online Debate Persuasion
Online debate forums provide users a platform to express their opinions on controversial topics while being exposed to opinions from diverse set of viewpoints.
Improving Machine Reading Comprehension with Contextualized Commonsense Knowledge
In this paper, we aim to extract commonsense knowledge to improve machine reading comprehension.
GRIT: Generative Role-filler Transformers for Document-level Event Entity Extraction
We revisit the classic problem of document-level role-filler entity extraction (REE) for template filling.
Interpreting Pretrained Contextualized Representations via Reductions to Static Embeddings
Contextualized representations (e. g. ELMo, BERT) have become the default pretrained representations for downstream NLP applications.
Document-Level Event Role Filler Extraction using Multi-Granularity Contextualized Encoding
Few works in the literature of event extraction have gone beyond individual sentences to make extraction decisions.
Event Extraction by Answering (Almost) Natural Questions
The problem of event extraction requires detecting the event trigger and extracting its corresponding arguments.
Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset
In this work we explore the task of instance segmentation with attribute localization, which unifies instance segmentation (detect and segment each object instance) and fine-grained visual attribute categorization (recognize one or multiple attributes).
Dialogue-Based Relation Extraction
We present the first human-annotated dialogue-based relation extraction (RE) dataset DialogRE, aiming to support the prediction of relation(s) between two arguments that appear in a dialogue.
Ranked #6 on
Dialog Relation Extraction
on DialogRE
(F1c (v1) metric)
The Role of Pragmatic and Discourse Context in Determining Argument Impact
Research in the social sciences and psychology has shown that the persuasiveness of an argument depends not only the language employed, but also on attributes of the source/communicator, the audience, and the appropriateness and strength of the argument's claims given the pragmatic and discourse context of the argument.
Persuasion of the Undecided: Language vs. the Listener
In a study of users of a popular debate platform, we find first that different combinations of linguistic features are critical for predicting persuasion outcomes for UNDECIDED versus DECIDED members of the audience.
Keeping Notes: Conditional Natural Language Generation with a Scratchpad Encoder
We introduce the Scratchpad Mechanism, a novel addition to the sequence-to-sequence (seq2seq) neural network architecture and demonstrate its effectiveness in improving the overall fluency of seq2seq models for natural language generation tasks.
Determining Relative Argument Specificity and Stance for Complex Argumentative Structures
Systems for automatic argument generation and debate require the ability to (1) determine the stance of any claims employed in the argument and (2) assess the specificity of each claim relative to the argument context.
A Corpus for Modeling User and Language Effects in Argumentation on Online Debating
Existing argumentation datasets have succeeded in allowing researchers to develop computational methods for analyzing the content, structure and linguistic features of argumentative text.
Exploring the Role of Prior Beliefs for Argument Persuasion
Public debate forums provide a common platform for exchanging opinions on a topic of interest.
Be Consistent! Improving Procedural Text Comprehension using Label Consistency
Our goal is procedural text comprehension, namely tracking how the properties of entities (e. g., their location) change with time given a procedural text (e. g., a paragraph about photosynthesis, a recipe).
Keeping Notes: Conditional Natural Language Generation with a Scratchpad Mechanism
We introduce the Scratchpad Mechanism, a novel addition to the sequence-to-sequence (seq2seq) neural network architecture and demonstrate its effectiveness in improving the overall fluency of seq2seq models for natural language generation tasks.
SPARSE: Structured Prediction using Argument-Relative Structured Encoding
We apply our approach to the second-order structured prediction task studied in the 2016/2017 Belief and Sentiment analysis evaluations (BeSt): given a document and its entities, relations, and events (including metadata and mentions), determine the sentiment of each entity towards every relation and event in the document.
Investigating Prior Knowledge for Challenging Chinese Machine Reading Comprehension
Machine reading comprehension tasks require a machine reader to answer questions relevant to the given document.
DREAM: A Challenge Data Set and Models for Dialogue-Based Reading Comprehension
We present DREAM, the first dialogue-based multiple-choice reading comprehension data set.
Improving Question Answering with External Knowledge
We focus on multiple-choice question answering (QA) tasks in subject areas such as science, where we require both broad background knowledge and the facts from the given subject-area reference corpus.
DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension
DREAM is likely to present significant challenges for existing reading comprehension systems: 84% of answers are non-extractive, 85% of questions require reasoning beyond a single sentence, and 34% of questions also involve commonsense knowledge.
Improving Machine Reading Comprehension with General Reading Strategies
Reading strategies have been shown to improve comprehension levels, especially for readers lacking adequate prior knowledge.
Ranked #7 on
Question Answering
on StoryCloze
Multi-Source Cross-Lingual Model Transfer: Learning What to Share
In this work, we focus on the multilingual transfer setting where training data in multiple source languages is leveraged to further boost target language performance.
Ranked #10 on
Cross-Lingual NER
on CoNLL Dutch
Zero-Resource Multilingual Model Transfer: Learning What to Share
In this work, we propose a zero-resource multilingual transfer learning model that can utilize training data in multiple source languages, while not requiring target language training data nor cross-lingual supervision.
Towards Dynamic Computation Graphs via Sparse Latent Structure
Deep NLP models benefit from underlying structures in the data---e. g., parse trees---typically extracted using off-the-shelf parsers.
Unsupervised Multilingual Word Embeddings
Multilingual Word Embeddings (MWEs) represent words from multiple languages in a single distributional vector space.
The Neural Painter: Multi-Turn Image Generation
In this work we combine two research threads from Vision/ Graphics and Natural Language Processing to formulate an image generation task conditioned on attributes in a multi-turn setting.
Nested Named Entity Recognition Revisited
We propose a novel recurrent neural network-based approach to simultaneously handle nested named entity recognition and nested entity mention detection.
Understanding the Effect of Gender and Stance in Opinion Expression in Debates on ``Abortion''
We use the gender and stance information to identify significant linguistic differences across individuals with different gender and stance.
Harvesting Paragraph-Level Question-Answer Pairs from Wikipedia
We study the task of generating from Wikipedia articles question-answer pairs that cover content beyond a single sentence.
Multinomial Adversarial Networks for Multi-Domain Text Classification
Many text classification tasks are known to be highly domain-dependent.
SparseMAP: Differentiable Sparse Structured Inference
Structured prediction requires searching over a combinatorial number of structures.
Identifying Where to Focus in Reading Comprehension for Neural Question Generation
A first step in the task of automatically generating questions for testing reading comprehension is to identify \textit{question-worthy} sentences, i. e. sentences in a text passage that humans find it worthwhile to ask questions about.
Going out on a limb: Joint Extraction of Entity Mentions and Relations without Dependency Trees
We also compare our model with an end-to-end tree-based LSTM model (SPTree) by Miwa and Bansal (2016) and show that our model performs within 1{\%} on entity mentions and 2{\%} on relations.
Ranked #9 on
Relation Extraction
on ACE 2004
Learning to Ask: Neural Question Generation for Reading Comprehension
We study automatic question generation for sentences from text passages in reading comprehension.
Argument Mining with Structured SVMs and RNNs
We propose a novel factor graph model for argument mining, designed for settings in which the argumentative relations in a document do not necessarily form a tree structure.
Summarizing Decisions in Spoken Meetings
This paper addresses the problem of summarizing decisions in spoken meetings: our goal is to produce a concise {\it decision abstract} for each meeting decision.
A Sentence Compression Based Framework to Query-Focused Multi-Document Summarization
We consider the problem of using sentence compression techniques to facilitate query-focused multi-document summarization.
Unsupervised Topic Modeling Approaches to Decision Summarization in Spoken Meetings
We present a token-level decision summarization framework that utilizes the latent topic structures of utterances to identify "summary-worthy" words.
Focused Meeting Summarization via Unsupervised Relation Extraction
We present a novel unsupervised framework for focused meeting summarization that views the problem as an instance of relation extraction.
Improving Agreement and Disagreement Identification in Online Discussions with A Socially-Tuned Sentiment Lexicon
For example, the isotonic CRF model achieves F1 scores of 0. 74 and 0. 67 for agreement and disagreement detection, when a linear chain CRF obtains 0. 58 and 0. 56 for the discussions on Wikipedia Talk pages.
Socially-Informed Timeline Generation for Complex Events
Existing timeline generation systems for complex events consider only information from traditional media, ignoring the rich social context provided by user-generated content that reveals representative public interests or insightful opinions.
Query-Focused Opinion Summarization for User-Generated Content
We present a submodular function-based framework for query-focused opinion summarization.
A Piece of My Mind: A Sentiment Analysis Approach for Online Dispute Detection
We investigate the novel task of online dispute detection and propose a sentiment analysis solution to the problem: we aim to identify the sequence of sentence-level sentiments expressed during a discussion and to use them as features in a classifier that predicts the DISPUTE/NON-DISPUTE label for the discussion as a whole.
Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification
To tackle the sentiment classification problem in low-resource languages without adequate annotated data, we propose an Adversarial Deep Averaging Network (ADAN) to transfer the knowledge learned from labeled data on a resource-rich source language to low-resource languages where only unlabeled data exists.
A Hierarchical Distance-dependent Bayesian Model for Event Coreference Resolution
We present a novel hierarchical distance-dependent Bayesian model for event coreference resolution.
Modeling Compositionality with Multiplicative Recurrent Neural Networks
We present the multiplicative recurrent neural network as a general model for compositional meaning in language, and evaluate it on the task of fine-grained sentiment analysis.
Deep Recursive Neural Networks for Compositionality in Language
In this work we introduce a new architecture --- a deep recursive neural network (deep RNN) --- constructed by stacking multiple recursive layers.
Joint Modeling of Opinion Expression Extraction and Attribute Classification
In this paper, we study the problems of opinion expression extraction and expression-level polarity and intensity classification.
Bidirectional Recursive Neural Networks for Token-Level Labeling with Structure
Recently, deep architectures, such as recurrent and recursive neural networks have been successfully applied to various natural language processing tasks.
Early Stage Influenza Detection from Twitter
In this paper, we investigate the real-time flu detection problem on Twitter data by proposing Flu Markov Network (Flu-MN): a spatio-temporal unsupervised Bayesian algorithm based on a 4 phase Markov Network, trying to identify the flu breakout at the earliest stage.
