Search Results for author:
Found 162 papers, 97 papers with code
Identifying Distributional Perspectives from Colingual Groups
Discrepancies exist among different cultures or languages.
Fantastic Questions and Where to Find Them: FairytaleQA – An Authentic Dataset for Narrative Comprehension
Through benchmarking with QG models, we show that the QG model trained on FairytaleQA is capable of asking high-quality and more diverse questions.
NewsEdits: A News Article Revision Dataset and a Novel Document-Level Reasoning Challenge
News article revision histories provide clues to narrative and factual evolution in news articles.
AESOP: Paraphrase Generation with Adaptive Syntactic Control
We propose to control paraphrase generation through carefully chosen target syntactic structures to generate more proper and higher quality paraphrases.
ESTER: A Machine Reading Comprehension Dataset for Reasoning about Event Semantic Relations
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.
Improving Pre-trained Vision-and-Language Embeddings for Phrase Grounding
Phrase grounding aims to map textual phrases to their associated image regions, which can be a prerequisite for multimodal reasoning and can benefit tasks requiring identifying objects based on language.
GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labeling
In this paper, we propose GenEARL, a training-free generative framework that harness the power of the modern generative models to understand event task descriptions given image contexts to perform the EARL task.
PhonologyBench: Evaluating Phonological Skills of Large Language Models
To this end, we present PhonologyBench, a novel benchmark consisting of three diagnostic tasks designed to explicitly test the phonological skills of LLMs in English: grapheme-to-phoneme conversion, syllable counting, and rhyme word generation.
Event Detection from Social Media for Epidemic Prediction
In our work, we pioneer exploiting Event Detection (ED) for better preparedness and early warnings of any upcoming epidemic by developing a framework to extract and analyze epidemic-related events from social media posts.
Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization
A common technique for aligning large language models (LLMs) relies on acquiring human preferences by comparing multiple generations conditioned on a fixed context.
Argument-Aware Approach To Event Linking
Event linking connects event mentions in text with relevant nodes in a knowledge base (KB).
Improving Event Definition Following For Zero-Shot Event Detection
We hypothesize that a diverse set of event types and definitions are the key for models to learn to follow event definitions while existing event extraction datasets focus on annotating many high-quality examples for a few event types.
DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation
We construct the DACO dataset, containing (1) 440 databases (of tabular data) collected from real-world scenarios, (2) ~2k query-answer pairs that can serve as weak supervision for model training, and (3) a concentrated but high-quality test set with human refined annotations that serves as our main evaluation benchmark.
On Prompt-Driven Safeguarding for Large Language Models
Prepending model inputs with safety prompts is a common practice for safeguarding large language models (LLMs) from complying with queries that contain harmful intents.
ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal Models
Our findings reveal a significant performance gap of 30. 8% between the best-performing LMM, GPT-4V(ision), and human capabilities using human evaluation indicating substantial room for improvement in context-sensitive text-rich visual reasoning.
DeepEdit: Knowledge Editing as Decoding with Constraints
To enforce these constraints, we utilize a depth-first search to adaptively substitute new knowledge for the LLMs' original reasoning steps, greedily seeking the optimal path of multi-hop reasoning with new knowledge.
Model Editing Can Hurt General Abilities of Large Language Models
One critical challenge that has emerged is the presence of hallucinations in the output of large language models (LLMs) due to false or outdated knowledge.
New Job, New Gender? Measuring the Social Bias in Image Generation Models
BiasPainter uses a diverse range of seed images of individuals and prompts the image generation models to edit these images using gender, race, and age-neutral queries.
AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation
Prior works on evaluating factual consistency of summarization often take the entailment-based approaches that first generate perturbed (factual inconsistent) summaries and then train a classifier on the generated data to detect the factually inconsistencies during testing time.
Abstractive Text Summarization
Natural Language Inference
+1
MacGyver: Are Large Language Models Creative Problem Solvers?
We explore the creative problem-solving capabilities of modern LLMs in a novel constrained setting.
TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extraction
In this work, we identify and address evaluation challenges, including inconsistency due to varying data assumptions or preprocessing steps, the insufficiency of current evaluation frameworks that may introduce dataset or data split bias, and the low reproducibility of some previous approaches.
Tracking the Newsworthiness of Public Documents
Journalists must find stories in huge amounts of textual data (e. g. leaks, bills, press releases) as part of their jobs: determining when and why text becomes news can help us understand coverage patterns and help us build assistive tools.
ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life Videos
Multimodal counterfactual reasoning is a vital yet challenging ability for AI systems.
Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks
Instruction tuning (IT) achieves impressive zero-shot generalization results by training large language models (LLMs) on a massive amount of diverse tasks with instructions.
BOOST: Harnessing Black-Box Control to Boost Commonsense in LMs' Generation
Large language models (LLMs) such as GPT-3 have demonstrated a strong capability to generate coherent and contextually relevant text.
Localizing Active Objects from Egocentric Vision with Symbolic World Knowledge
The ability to actively ground task instructions from an egocentric view is crucial for AI agents to accomplish tasks or assist humans virtually.
Evaluating Large Language Models on Controlled Generation Tasks
While recent studies have looked into the abilities of large language models in various benchmark tasks, including question generation, reading comprehension, multilingual and etc, there have been few studies looking into the controllability of large language models on generation tasks.
"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters
Through benchmarking evaluation on 2 popular LLMs- ChatGPT and Alpaca, we reveal significant gender biases in LLM-generated recommendation letters.
Mitigating Bias for Question Answering Models by Tracking Bias Influence
Based on the intuition that a model would lean to be more biased if it learns from a biased example, we measure the bias level of a query instance by observing its influence on another instance.
Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems
Recent advancements in Large Language Models empower them to follow freeform instructions, including imitating generic or specific demographic personas in conversations.
MIDDAG: Where Does Our News Go? Investigating Information Diffusion via Community-Level Information Pathways
We present MIDDAG, an intuitive, interactive system that visualizes the information propagation paths on social media triggered by COVID-19-related news articles accompanied by comprehensive insights, including user/community susceptibility level, as well as events and popular opinions raised by the crowd while propagating the information.
Contextual Label Projection for Cross-Lingual Structured Prediction
Label projection, which involves obtaining translated labels and texts jointly, is essential for leveraging machine translation to facilitate cross-lingual transfer in structured prediction tasks.
RLCD: Reinforcement Learning from Contrastive Distillation for Language Model Alignment
We propose Reinforcement Learning from Contrastive Distillation (RLCD), a method for aligning language models to follow principles expressed in natural language (e. g., to be more harmless) without using human feedback.
Next Steps for Human-Centered Generative AI: A Technical Perspective
Through iterative, cross-disciplinary discussions, we define and propose next-steps for Human-centered Generative AI (HGAI).
On Compositionality and Improved Training of NADO
NeurAlly-Decomposed Oracle (NADO) is a powerful approach for controllable generation with large language models.
Open-Domain Text Evaluation via Meta Distribution Modeling
We investigate MDM for open-domain text generation evaluation under two paradigms: 1) \emph{Generative} MDM, which leverages the Meta-Distribution Methods to generate in-domain negative samples for training discriminator-based metrics; 2) \emph{Discriminative} MDM, which directly uses distribution discrepancies between two language models for evaluation.
Unsupervised Melody-to-Lyric Generation
Automatic melody-to-lyric generation is a task in which song lyrics are generated to go with a given melody.
Are Fairy Tales Fair? Analyzing Gender Bias in Temporal Narrative Event Chains of Children's Fairy Tales
Social biases and stereotypes are embedded in our culture in part through their presence in our stories, as evidenced by the rich history of humanities and social science literature analyzing such biases in children stories.
AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction Model
However, existing generation-based EAE models mostly focus on problem re-formulation and prompt design, without incorporating additional information that has been shown to be effective for classification-based models, such as the abstract meaning representation (AMR) of the input passages.
Code-Switched Text Synthesis in Unseen Language Pairs
In this work, we study the problem of synthesizing code-switched texts for language pairs absent from the training data.
Identifying Informational Sources in News Articles
News articles are driven by the informational sources journalists use in reporting.
STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models
Information extraction tasks such as event extraction require an in-depth understanding of the output structure and sub-task dependencies.
Gender Biases in Automatic Evaluation Metrics for Image Captioning
Model-based evaluation metrics (e. g., CLIPScore and GPTScore) have demonstrated decent correlations with human judgments in various language generation tasks.
Masked Path Modeling for Vision-and-Language Navigation
In this paper, we introduce a masked path modeling (MPM) objective, which pretrains an agent using self-collected data for downstream navigation tasks.
Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuning
Our experiments show that models trained on simplified task definition or delusive examples can achieve comparable performance to the ones trained on the original instructions and examples.
Unsupervised Melody-Guided Lyrics Generation
At inference time, we leverage the crucial alignments between melody and lyrics and compile the given melody into constraints to guide the generation process.
ACCENT: An Automatic Event Commonsense Evaluation Metric for Open-Domain Dialogue Systems
We take the first step by focusing on event commonsense that considers events and their relations, and is crucial in both dialogues and general commonsense reasoning.
Tractable Control for Autoregressive Language Generation
To overcome this challenge, we propose to use tractable probabilistic models (TPMs) to impose lexical constraints in autoregressive text generation models, which we refer to as GeLaTo (Generating Language with Tractable Constraints).
Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuning
Dialogue state tracking (DST) is an important step in dialogue management to keep track of users' beliefs.
Sequentially Controlled Text Generation
While GPT-2 generates sentences that are remarkably human-like, longer documents can ramble and do not follow human-like writing structure.
Generalized Decoding for Pixel, Image, and Language
We present X-Decoder, a generalized decoding model that can predict pixel-level segmentation and language tokens seamlessly.
Ranked #4 on
Instance Segmentation
on ADE20K val
(using extra training data)
DOC: Improving Long Story Coherence With Detailed Outline Control
In human evaluations of automatically generated stories, DOC substantially outperforms a strong Re3 baseline (Yang et al., 2022) on plot coherence (22. 5% absolute gain), outline relevance (28. 2%), and interestingness (20. 7%).
Towards Robust NLG Bias Evaluation with Syntactically-diverse Prompts
These fixed prefix templates could themselves be specific in terms of styles or linguistic structures, which may lead to unreliable fairness conclusions that are not representative of the general trends from tone varying prompts.
A Moral- and Event- Centric Inspection of Gender Bias in Fairy Tales at A Large Scale
Our analysis further reveal stereotypical portrayals of both male and female characters in terms of moral foundations and events.
A Unified Framework for Pun Generation with Humor Principles
We propose a unified framework to generate both homophonic and homographic puns to resolve the split-up in existing works.
ExPUNations: Augmenting Puns with Keywords and Explanations
The tasks of humor understanding and generation are challenging and subjective even for humans, requiring commonsense and real-world knowledge to master.
Context-Situated Pun Generation
In this work, we propose a new task, context-situated pun generation, where a specific context represented by a set of keywords is provided, and the task is to first identify suitable pun words that are appropriate for the context, then generate puns based on the context keywords and the identified pun words.
EnDex: Evaluation of Dialogue Engagingness at Scale
We propose EnDex, the first human-reaction based model to evaluate dialogue engagingness.
Character-Centric Story Visualization via Visual Planning and Token Alignment
This task requires machines to 1) understand long text inputs and 2) produce a globally consistent image sequence that illustrates the contents of the story.
Re3: Generating Longer Stories With Recursive Reprompting and Revision
We consider the problem of automatically generating longer stories of over two thousand words.
Controllable Text Generation for Open-Domain Creativity and Fairness
Recent advances in large pre-trained language models have demonstrated strong results in generating natural languages and significantly improved performances for many natural language generation (NLG) applications such as machine translation and text summarization.
NECE: Narrative Event Chain Extraction Toolkit
To understand a narrative, it is essential to comprehend the temporal event flows, especially those associated with main characters; however, this can be challenging with lengthy and unstructured narrative texts.
DICE: Data-Efficient Clinical Event Extraction with Generative Models
Event extraction for the clinical domain is an under-explored research area.
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone
Vision-language (VL) pre-training has recently received considerable attention.
Ranked #1 on
Phrase Grounding
on Flickr30k Entities Dev
NewsEdits: A News Article Revision Dataset and a Document-Level Reasoning Challenge
News article revision histories provide clues to narrative and factual evolution in news articles.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
FOAM: A Follower-aware Speaker Model For Vision-and-Language Navigation
The speaker-follower models have proven to be effective in vision-and-language navigation, where a speaker model is used to synthesize new instructions to augment the training data for a follower navigation model.
Controllable Text Generation with Neurally-Decomposed Oracle
We propose a general and efficient framework to control auto-regressive generation models with NeurAlly-Decomposed Oracle (NADO).
GENEVA: Benchmarking Generalizability for Event Argument Extraction with Hundreds of Event Types and Argument Roles
We utilize this ontology to further introduce GENEVA, a diverse generalizability benchmarking dataset comprising four test suites, aimed at evaluating models' ability to handle limited data and unseen event type generalization.
Learning Action Conditions from Instructional Manuals for Instruction Understanding
The ability to infer pre- and postconditions of an action is vital for comprehending complex instructions, and is essential for applications such as autonomous instruction-guided agents and assistive AI that supports humans to perform physical tasks.
Helpfulness and Fairness of Task-Oriented Dialogue Systems
Then, we collect human annotations for the helpfulness of dialogue responses based on our definition and build a classifier to automatically determine the helpfulness of a response.
TAGPRIME: A Unified Framework for Relational Structure Extraction
In this work, we propose to take a unified view of all these tasks and introduce TAGPRIME to address relational structure extraction problems.
Sibylvariant Transformations for Robust Text Classification
The vast majority of text transformation techniques in NLP are inherently limited in their ability to expand input space coverage due to an implicit constraint to preserve the original class label.
Go Back in Time: Generating Flashbacks in Stories with Event Temporal Prompts
Stories or narratives are comprised of a sequence of events.
AmbiPun: Generating Humorous Puns with Ambiguous Context
In this paper, we propose a simple yet effective way to generate pun sentences that does not require any training on existing puns.
Zero-shot Sonnet Generation with Discourse-level Planning and Aesthetics Features
Poetry generation, and creative language generation in general, usually suffers from the lack of large training data.
Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension
Through benchmarking with QG models, we show that the QG model trained on FairytaleQA is capable of asking high-quality and more diverse questions.
Ranked #1 on
Question Generation
on FairytaleQA
DEAM: Dialogue Coherence Evaluation using AMR-based Semantic Manipulations
We also show that DEAM can distinguish between coherent and incoherent dialogues generated by baseline manipulations, whereas those baseline models cannot detect incoherent examples generated by DEAM.
Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction
We present a study on leveraging multilingual pre-trained generative language models for zero-shot cross-lingual event argument extraction (EAE).
Zero-shot Commonsense Question Answering with Cloze Translation and Consistency Optimization
In this paper, we instead focus on better utilizing the \textit{implicit knowledge} stored in pre-trained language models.
An Empirical Study of Training End-to-End Vision-and-Language Transformers
Vision-and-language (VL) pre-training has proven to be highly effective on various VL downstream tasks.
Ranked #20 on
Cross-Modal Retrieval
on COCO 2014
(using extra training data)
Understanding Multimodal Procedural Knowledge by Sequencing Multimodal Instructional Manuals
The ability to sequence unordered events is an essential skill to comprehend and reason about real world task procedures, which often requires thorough understanding of temporal common sense and multimodal information, as these procedures are often communicated through a combination of texts and images.
On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark
We propose a taxonomy for dialogue safety specifically designed to capture unsafe behaviors in human-bot dialogue settings, with focuses on context-sensitive unsafety, which is under-explored in prior works.
Socially Aware Bias Measurements for Hindi Language Representations
Language representations are efficient tools used across NLP applications, but they are strife with encoded societal biases.
HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning
Taxonomies are valuable resources for many applications, but the limited coverage due to the expensive manual curation process hinders their general applicability.
Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning
Commonsense is defined as the knowledge that is shared by everyone.
Ranked #1 on
Visual Commonsense Reasoning
on GD-VCR
Cultural Vocal Bursts Intensity Prediction
Visual Commonsense Reasoning
Document-level Entity-based Extraction as Template Generation
Document-level entity-based extraction (EE), aiming at extracting entity-centric information such as entity roles and entity relations, is key to automatic knowledge acquisition from text corpora for various domains.
Ranked #1 on
Role-filler Entity Extraction
on MUC-4
HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledge
A hyperbole is an intentional and creative exaggeration not to be taken literally.
Paraphrase Generation as Unsupervised Machine Translation
Then based on the paraphrase pairs produced by these UMT models, a unified surrogate model can be trained to serve as the final \sts model to generate paraphrases, which can be directly used for test in the unsupervised setup, or be finetuned on labeled datasets in the supervised setup.
DEGREE: A Data-Efficient Generation-Based Event Extraction Model
Given a passage and a manually designed prompt, DEGREE learns to summarize the events mentioned in the passage into a natural sentence that follows a predefined pattern.
On Measures of Biases and Harms in NLP
Recent studies show that Natural Language Processing (NLP) technologies propagate societal biases about demographic groups associated with attributes such as gender, race, and nationality.
Men Are Elected, Women Are Married: Events Gender Bias on Wikipedia
Human activities can be seen as sequences of events, which are crucial to understanding societies.
Metaphor Generation with Conceptual Mappings
Guided by conceptual metaphor theory, we propose to control the generation process by encoding conceptual mappings between cognitive domains to generate meaningful metaphoric expressions.
COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences
To this end, we introduce a new commonsense reasoning benchmark dataset comprising natural language true/false statements, with each sample paired with its complementary counterpart, resulting in 4k sentence pairs.
``Nice Try, Kiddo'': Investigating Ad Hominems in Dialogue Responses
Ad hominem attacks are those that target some feature of a person{'}s character instead of the position the person is maintaining.
Societal Biases in Language Generation: Progress and Challenges
Technology for language generation has advanced rapidly, spurred by advancements in pre-training large models on massive amounts of data and the need for intelligent agents to communicate in a natural manner.
"Don't quote me on that": Finding Mixtures of Sources in News Articles
Journalists publish statements provided by people, or \textit{sources} to contextualize current events, help voters make informed decisions, and hold powerful individuals accountable.
Modeling "Newsworthiness" for Lead-Generation Across Corpora
Journalists obtain "leads", or story ideas, by reading large corpora of government records: court cases, proposed bills, etc.
Revealing Persona Biases in Dialogue Systems
Dialogue systems in the form of chatbots and personal assistants are being increasingly integrated into people's lives.
Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training
Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potential for zero-shot cross-lingual transfer.
ESTER: A Machine Reading Comprehension Dataset for Event Semantic Relation Reasoning
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.
Plot-guided Adversarial Example Construction for Evaluating Open-domain Story Generation
We propose to tackle these issues by generating a more comprehensive set of implausible stories using {\em plots}, which are structured representations of controllable factors used to generate stories.
MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding
Generating metaphors is a challenging task as it requires a proper understanding of abstract concepts, making connections between unrelated concepts, and deviating from the literal meaning.
InsNet: An Efficient, Flexible, and Performant Insertion-based Text Generation Model
We propose InsNet, an expressive insertion-based text generator with efficient training and flexible decoding (parallel or sequential).
DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation
Having engaging and informative conversations with users is the utmost goal for open-domain conversational systems.
EventPlus: A Temporal Event Understanding Pipeline
We present EventPlus, a temporal event understanding pipeline that integrates various state-of-the-art event understanding components including event trigger and type detection, event argument detection, event duration and temporal relation extraction.
Discourse-level Relation Extraction via Graph Pooling
The ability to capture complex linguistic structures and long-term dependencies among words in the passage is essential for discourse-level relation extraction (DRE) tasks.
ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning
While pre-trained language models (PTLMs) have achieved noticeable success on many NLP tasks, they still struggle for tasks that require event temporal reasoning, which is essential for event-centric applications.
Ranked #1 on
Question Answering
on Torque
A Paragraph-level Multi-task Learning Model for Scientific Fact-Verification
Even for domain experts, it is a non-trivial task to verify a scientific claim by providing supporting or refuting evidence rationales.
MELINDA: A Multimodal Dataset for Biomedical Experiment Method Classification
We introduce a new dataset, MELINDA, for Multimodal biomEdicaL experImeNt methoD clAssification.
Detecting Social Media Manipulation in Low-Resource Languages
Social media have been deliberately used for malicious purposes, including political manipulation and disinformation.
"Nice Try, Kiddo": Investigating Ad Hominems in Dialogue Responses
Ad hominem attacks are those that target some feature of a person's character instead of the position the person is maintaining.
Document-level Event Extraction with Efficient End-to-end Learning of Cross-event Dependencies
Fully understanding narratives often requires identifying events in the context of whole documents and modeling the event relations.
GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event Extraction
Recent progress in cross-lingual relation and event extraction use graph convolutional networks (GCNs) with universal dependency parses to learn language-agnostic sentence representations such that models trained on one language can be applied to other languages.
STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation
Systems for story generation are asked to produce plausible and enjoyable stories given an input context.
Content Planning for Neural Story Generation with Aristotelian Rescoring
Long-form narrative text generated from large language models manages a fluent impersonation of human writing, but only at the local sentence level, and lacks structure or global cohesion.
Biomedical Event Extraction with Hierarchical Knowledge Graphs
To better recognize the trigger words, each sentence is first grounded to a sentence graph based on a jointly modeled hierarchical knowledge graph from UMLS.
Ranked #2 on
Event Extraction
on GENIA
Generating similes effortlessly like a Pro: A Style Transfer Approach for Simile Generation
We also show how replacing literal sentences with similes from our best model in machine generated stories improves evocativeness and leads to better acceptance by human judges.
Domain Knowledge Empowered Structured Neural Net for End-to-End Event Temporal Relation Extraction
Extracting event temporal relations is a critical task for information extraction and plays an important role in natural language understanding.
R\^3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge
We propose an unsupervised approach for sarcasm generation based on a non-sarcastic input sentence.
Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering
In this paper, we augment a general commonsense QA framework with a knowledgeable path generator.
Towards Controllable Biases in Language Generation
We present a general approach towards controllable societal biases in natural language generation (NLG).
TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions
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
$R^3$: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge
We propose an unsupervised approach for sarcasm generation based on a non-sarcastic input sentence.
Identifying Distributional Perspective Differences from Colingual Groups
Perspective differences exist among different cultures or languages.
Predictive Engagement: An Efficient Metric For Automatic Evaluation of Open-Domain Dialogue Systems
In this paper, we investigate the possibility and efficacy of estimating utterance-level engagement and define a novel metric, {\em predictive engagement}, for automatic evaluation of open-domain dialogue systems.
Do Nuclear Submarines Have Nuclear Captains? A Challenge Dataset for Commonsense Reasoning over Adjectives and Objects
This provides evidence that the amount of commonsense knowledge encoded in these language models does not extend far beyond that already baked into the word embeddings.
Man is to Person as Woman is to Location: Measuring Gender Bias in Named Entity Recognition
We study the bias in several state-of-the-art named entity recognition (NER) models---specifically, a difference in the ability to recognize male and female names as PERSON entity types.
Learning A Unified Named Entity Tagger From Multiple Partially Annotated Corpora For Efficient Adaptation
Named entity recognition (NER) identifies typed entity mentions in raw text.
Ranked #14 on
Named Entity Recognition (NER)
on NCBI-disease
Deep Structured Neural Network for Event Temporal Relation Extraction
We propose a novel deep structured learning framework for event temporal relation extraction.
Cross-lingual Dependency Parsing with Unlabeled Auxiliary Languages
We conduct experiments on cross-lingual dependency parsing where we train a dependency parser on a source language and transfer it to a wide range of target languages.
Espresso: A Fast End-to-end Neural Speech Recognition Toolkit
We present Espresso, an open-source, modular, extensible end-to-end neural automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch and the popular neural machine translation toolkit fairseq.
Ranked #1 on
Speech Recognition
on Hub5'00 CallHome
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Scientific Discourse Tagging for Evidence Extraction
We apply richly contextualized deep representation learning pre-trained on biomedical domain corpus to the analysis of scientific discourse structures and the extraction of "evidence fragments" (i. e., the text in the results section describing data presented in a specified subfigure) from a set of biomedical experimental research articles.
What Matters for Neural Cross-Lingual Named Entity Recognition: An Empirical Analysis
While recent work has shown promising results on cross-lingual transfer from high-resource languages to low-resource languages, it is unclear what knowledge is transferred.
Target Language-Aware Constrained Inference for Cross-lingual Dependency Parsing
Experiments show that the Lagrangian relaxation and posterior regularization inference improve the performances on 15 and 17 out of 19 target languages, respectively.
The Woman Worked as a Babysitter: On Biases in Language Generation
We present a systematic study of biases in natural language generation (NLG) by analyzing text generated from prompts that contain mentions of different demographic groups.
Joint Event and Temporal Relation Extraction with Shared Representations and Structured Prediction
We propose a joint event and temporal relation extraction model with shared representation learning and structured prediction.
Event Extraction
Joint Event and Temporal Relation Extraction
+4
Contextualized Word Embeddings Enhanced Event Temporal Relation Extraction for Story Understanding
In this work, we establish strong baselines for event temporal relation extraction on two under-explored story narrative datasets: Richer Event Description (RED) and Causal and Temporal Relation Scheme (CaTeRS).
Better Automatic Evaluation of Open-Domain Dialogue Systems with Contextualized Embeddings
Despite advances in open-domain dialogue systems, automatic evaluation of such systems is still a challenging problem.
Pun Generation with Surprise
We tackle the problem of generating a pun sentence given a pair of homophones (e. g., "died" and "dyed").
Plan, Write, and Revise: an Interactive System for Open-Domain Story Generation
We compare different varieties of interaction in story-writing, story-planning, and diversity controls under time constraints, and show that increased types of human collaboration at both planning and writing stages results in a 10-50% improvement in story quality as compared to less interactive baselines.
Plan-And-Write: Towards Better Automatic Storytelling
Automatic storytelling is challenging since it requires generating long, coherent natural language to describes a sensible sequence of events.
On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing
Different languages might have different word orders.
Towards Controllable Story Generation
We present a general framework of analyzing existing story corpora to generate controllable and creative new stories.
Scalable Construction and Reasoning of Massive Knowledge Bases
In today{'}s information-based society, there is abundant knowledge out there carried in the form of natural language texts (e. g., news articles, social media posts, scientific publications), which spans across various domains (e. g., corporate documents, advertisements, legal acts, medical reports), which grows at an astonishing rate.
Stack-Pointer Networks for Dependency Parsing
Combining pointer networks~\citep{vinyals2015pointer} with an internal stack, the proposed model first reads and encodes the whole sentence, then builds the dependency tree top-down (from root-to-leaf) in a depth-first fashion.
Ranked #14 on
Dependency Parsing
on Penn Treebank
Multi-task Learning for Universal Sentence Embeddings: A Thorough Evaluation using Transfer and Auxiliary Tasks
Learning distributed sentence representations is one of the key challenges in natural language processing.
Style Transfer in Text: Exploration and Evaluation
Results show that the proposed content preservation metric is highly correlate to human judgments, and the proposed models are able to generate sentences with higher style transfer strength and similar content preservation score comparing to auto-encoder.
Ranked #5 on
Unsupervised Text Style Transfer
on Yelp
A Multi-task Learning Approach to Adapting Bilingual Word Embeddings for Cross-lingual Named Entity Recognition
We show how to adapt bilingual word embeddings (BWE{'}s) to bootstrap a cross-lingual name-entity recognition (NER) system in a language with no labeled data.
Cross-Sentence N-ary Relation Extraction with Graph LSTMs
Past work in relation extraction has focused on binary relations in single sentences.
Multi-task Domain Adaptation for Sequence Tagging
Many domain adaptation approaches rely on learning cross domain shared representations to transfer the knowledge learned in one domain to other domains.
Improving Named Entity Recognition for Chinese Social Media with Word Segmentation Representation Learning
Named entity recognition, and other information extraction tasks, frequently use linguistic features such as part of speech tags or chunkings.
Modeling Word Forms Using Latent Underlying Morphs and Phonology
Given some surface word types of a concatenative language along with the abstract morpheme sequences that they express, we show how to recover consistent underlying forms for these morphemes, together with the (stochastic) phonology that maps each concatenation of underlying forms to a surface form.
