Search Results for author:
Found 96 papers, 22 papers with code
An Analysis of Capsule Networks for Part of Speech Tagging in High- and Low-resource Scenarios
Neural networks are a common tool in NLP, but it is not always clear which architecture to use for a given task.
A STEP towards Interpretable Multi-Hop Reasoning:Bridge Phrase Identification and Query Expansion
Through an evaluation on HotpotQA, a popular dataset for multi-hop QA, we show that our method yields: (a) improved evidence retrieval, (b) improved QA performance when using the retrieved sentences; and (c) effective and faithful explanations when answers are provided.
Do Transformer Networks Improve the Discovery of Rules from Text?
With their Discovery of Inference Rules from Text (DIRT) algorithm, Lin and Pantel (2001) made a seminal contribution to the field of rule acquisition from text, by adapting the distributional hypothesis of Harris (1954) to rules that model binary relations such as X treat Y. DIRT’s relevance is renewed in today’s neural era given the recent focus on interpretability in the field of natural language processing.
Taxonomy Builder: a Data-driven and User-centric Tool for Streamlining Taxonomy Construction
An existing domain taxonomy for normalizing content is often assumed when discussing approaches to information extraction, yet often in real-world scenarios there is none. When one does exist, as the information needs shift, it must be continually extended.
Combining Extraction and Generation for Constructing Belief-Consequence Causal Links
In this paper, we introduce and justify a new task—causal link extraction based on beliefs—and do a qualitative analysis of the ability of a large language model—InstructGPT-3—to generate implicit consequences of beliefs.
Students Who Study Together Learn Better: On the Importance of Collective Knowledge Distillation for Domain Transfer in Fact Verification
While neural networks produce state-of-the- art performance in several NLP tasks, they generally depend heavily on lexicalized information, which transfer poorly between domains.
Interpretability Rules: Jointly Bootstrapping a Neural Relation Extractorwith an Explanation Decoder
We introduce a method that transforms a rule-based relation extraction (RE) classifier into a neural one such that both interpretability and performance are achieved.
Do Transformers Dream of Inference, or Can Pretrained Generative Models Learn Implicit Inferential Rules?
Large pretrained language models (LM) have been used successfully for multi-hop question answering.
Low Resource Causal Event Detection from Biomedical Literature
Recognizing causal precedence relations among the chemical interactions in biomedical literature is crucial to understanding the underlying biological mechanisms.
A Human-machine Interface for Few-shot Rule Synthesis for Information Extraction
We propose a system that assists a user in constructing transparent information extraction models, consisting of patterns (or rules) written in a declarative language, through program synthesis. Users of our system can specify their requirements through the use of examples, which are collected with a search interface. The rule-synthesis system proposes rule candidates and the results of applying them on a textual corpus; the user has the option to accept the candidate, request another option, or adjust the examples provided to the system. Through an interactive evaluation, we show that our approach generates high-precision rules even in a 1-shot setting.
PatternRank: Jointly Ranking Patterns and Extractions for Relation Extraction Using Graph-Based Algorithms
In this paper we revisit the direction of using lexico-syntactic patterns for relation extraction instead of today’s ubiquitous neural classifiers.
From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples
We analyze how well pre-trained large language models (e. g., Llama2, GPT-4, Claude 3, etc) can do linear and non-linear regression when given in-context examples, without any additional training or gradient updates.
Towards Realistic Few-Shot Relation Extraction: A New Meta Dataset and Evaluation
We introduce a meta dataset for few-shot relation extraction, which includes two datasets derived from existing supervised relation extraction datasets NYT29 (Takanobu et al., 2019; Nayak and Ng, 2020) and WIKIDATA (Sorokin and Gurevych, 2017) as well as a few-shot form of the TACRED dataset (Sabo et al., 2021).
ELLEN: Extremely Lightly Supervised Learning For Efficient Named Entity Recognition
In a zero-shot setting, ELLEN also achieves over 75% of the performance of a strong, fully supervised model trained on gold data.
Best of Both Worlds: A Pliable and Generalizable Neuro-Symbolic Approach for Relation Classification
Human interventions to the rules for the TACRED relation \texttt{org:parents} boost the performance on that relation by as much as 26\% relative improvement, without negatively impacting the other relations, and without retraining the semantic matching component.
Enhancing Transformer RNNs with Multiple Temporal Perspectives
Further, the additional parameters necessary for the multiple temporal perspectives are fine-tuned with minimal computational overhead, avoiding the need for a full pre-training.
Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models
We propose the Data Contamination Quiz (DCQ), a simple and effective approach to detect data contamination in large language models (LLMs) and estimate the amount of it.
Divide & Conquer for Entailment-aware Multi-hop Evidence Retrieval
However, semantic equivalence is not the only relevance signal that needs to be considered when retrieving evidences for multi-hop questions.
Perturbation-based Active Learning for Question Answering
Building a question answering (QA) model with less annotation costs can be achieved by utilizing active learning (AL) training strategy.
Time Travel in LLMs: Tracing Data Contamination in Large Language Models
To estimate contamination of individual instances, we employ "guided instruction:" a prompt consisting of the dataset name, partition type, and the random-length initial segment of a reference instance, asking the LLM to complete it.
Do not Mask Randomly: Effective Domain-adaptive Pre-training by Masking In-domain Keywords
We propose a novel task-agnostic in-domain pre-training method that sits between generic pre-training and fine-tuning.
Improving Zero-shot Relation Classification via Automatically-acquired Entailment Templates
While fully supervised relation classification (RC) models perform well on large-scale datasets, their performance drops drastically in low-resource settings.
Synthetic Dataset for Evaluating Complex Compositional Knowledge for Natural Language Inference
To this end, we modify the original texts using a set of phrases - modifiers that correspond to universal quantifiers, existential quantifiers, negation, and other concept modifiers in Natural Logic (NL) (MacCartney, 2009).
It is not Sexually Suggestive, It is Educative. Separating Sex Education from Suggestive Content on TikTok Videos
Such a dataset is necessary to address the challenge of distinguishing between sexually suggestive content and virtual sex education videos on TikTok.
Explainable Verbal Reasoner Plus (EVR+): A Natural Language Reasoning Framework that Supports Diverse Compositional Reasoning
Languages models have been successfully applied to a variety of reasoning tasks in NLP, yet the language models still suffer from compositional generalization.
Validity Assessment of Legal Will Statements as Natural Language Inference
This work introduces a natural language inference (NLI) dataset that focuses on the validity of statements in legal wills.
BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examples
We introduce a novel semi-supervised procedure that bootstraps an NLI dataset from existing biomedical dataset that pairs mechanisms with experimental evidence in abstracts.
Ranked #1 on
Natural Language Inference
on BioNLI
A Compact Pretraining Approach for Neural Language Models
We construct these compact subsets from the unstructured data using a combination of abstractive summaries and extractive keywords.
Learning Open Domain Multi-hop Search Using Reinforcement Learning
We propose a method to teach an automated agent to learn how to search for multi-hop paths of relations between entities in an open domain.
SuMe: A Dataset Towards Summarizing Biomedical Mechanisms
We leverage this structure and create a summarization task, where the input is a collection of sentences and the main entities in an abstract, and the output includes the relationship and a sentence that summarizes the mechanism.
Better Retrieval May Not Lead to Better Question Answering
Considerable progress has been made recently in open-domain question answering (QA) problems, which require Information Retrieval (IR) and Reading Comprehension (RC).
It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers
Our approach uses a multi-task learning architecture, which jointly trains a classifier for relation extraction, and a sequence model that labels words in the context of the relation that explain the decisions of the relation classifier.
From Examples to Rules: Neural Guided Rule Synthesis for Information Extraction
While deep learning approaches to information extraction have had many successes, they can be difficult to augment or maintain as needs shift.
Automatic Correction of Syntactic Dependency Annotation Differences
Annotation inconsistencies between data sets can cause problems for low-resource NLP, where noisy or inconsistent data cannot be as easily replaced compared with resource-rich languages.
Informal Persian Universal Dependency Treebank
We then investigate the parsing of informal Persian by training two dependency parsers on existing formal treebanks and evaluating them on out-of-domain data, i. e. the development set of our informal treebank.
Neural Architectures for Biological Inter-Sentence Relation Extraction
We introduce a family of deep-learning architectures for inter-sentence relation extraction, i. e., relations where the participants are not necessarily in the same sentence.
How May I Help You? Using Neural Text Simplification to Improve Downstream NLP Tasks
The general goal of text simplification (TS) is to reduce text complexity for human consumption.
Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading
We propose a simple and effective strategy for data augmentation for low-resource machine reading comprehension (MRC).
Explainable Multi-hop Verbal Reasoning Through Internal Monologue
Moreover, models trained on simpler tasks tend to fail when directly tested on more complex problems.
If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering
We specifically emphasize on the importance of retrieving evidence jointly by showing several comparative analyses to other methods that retrieve and rerank evidence sentences individually.
Data and Model Distillation as a Solution for Domain-transferable Fact Verification
While neural networks produce state-of-the-art performance in several NLP tasks, they generally depend heavily on lexicalized information, which transfer poorly between domains.
An Unsupervised Method for Learning Representations of Multi-word Expressions for Semantic Classification
This paper explores an unsupervised approach to learning a compositional representation function for multi-word expressions (MWEs), and evaluates it on the Tratz dataset, which associates two-word expressions with the semantic relation between the compound constituents (e. g. the label employer is associated with the noun compound government agency) (Tratz, 2011).
The Language of Food during the Pandemic: Hints about the Dietary Effects of Covid-19
Specifically, we analyze over770, 000 tweets published during the lockdown and the equivalent period in the five previous years and highlight several worrying trends.
Using the Hammer Only on Nails: A Hybrid Method for Evidence Retrieval for Question Answering
Evidence retrieval is a key component of explainable question answering (QA).
Exploring Interpretability in Event Extraction: Multitask Learning of a Neural Event Classifier and an Explanation Decoder
Our approach uses an encoder-decoder architecture, which jointly trains a classifier for event extraction, and a rule decoder that generates syntactico-semantic rules that explain the decisions of the event classifier.
Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering
Evidence retrieval is a critical stage of question answering (QA), necessary not only to improve performance, but also to explain the decisions of the corresponding QA method.
Parsing as Tagging
For example, for the sentence John eats cake, the tag to be predicted for the token cake is -1 because its head (eats) occurs one token to the left.
Towards the Necessity for Debiasing Natural Language Inference Datasets
Modeling natural language inference is a challenging task.
Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering
We show that the sentences selected by our method improve the performance of a state-of-the-art supervised QA model on two multi-hop QA datasets: AI2's Reasoning Challenge (ARC) and Multi-Sentence Reading Comprehension (MultiRC).
What does the language of foods say about us?
Second, we investigate the effect of socioeconomic factors (income, poverty, and education) on predicting state-level T2DM rates.
On the Importance of Delexicalization for Fact Verification
As expected, even though this method achieves high accuracy when evaluated in the same domain, the performance in the target domain is poor, marginally above chance. To mitigate this dependence on lexicalized information, we experiment with several strategies for masking out names by replacing them with their semantic category, coupled with a unique identifier to mark that the same or new entities are referenced between claim and evidence.
University of Arizona at SemEval-2019 Task 12: Deep-Affix Named Entity Recognition of Geolocation Entities
We present the Named Entity Recognition (NER) and disambiguation model used by the University of Arizona team (UArizona) for the SemEval 2019 task 12.
Eidos, INDRA, \& Delphi: From Free Text to Executable Causal Models
Building causal models of complicated phenomena such as food insecurity is currently a slow and labor-intensive manual process.
Alignment over Heterogeneous Embeddings for Question Answering
We propose a simple, fast, and mostly-unsupervised approach for non-factoid question answering (QA) called Alignment over Heterogeneous Embeddings (AHE).
Enabling Search and Collaborative Assembly of Causal Interactions Extracted from Multilingual and Multi-domain Free Text
Many of the most pressing current research problems (e. g., public health, food security, or climate change) require multi-disciplinary collaborations.
Exploration of Noise Strategies in Semi-supervised Named Entity Classification
Our work aims to address this gap by exploring different noise strategies for the semi-supervised named entity classification task, including statistical methods such as adding Gaussian noise to input embeddings, and linguistically-inspired ones such as dropping words and replacing words with their synonyms.
Semi-Supervised Teacher-Student Architecture for Relation Extraction
Generating a large amount of training data for information extraction (IE) is either costly (if annotations are created manually), or runs the risk of introducing noisy instances (if distant supervision is used).
Understanding the Polarity of Events in the Biomedical Literature: Deep Learning vs. Linguistically-informed Methods
An important task in the machine reading of biochemical events expressed in biomedical texts is correctly reading the polarity, i. e., attributing whether the biochemical event is a promotion or an inhibition.
A mostly unlexicalized model for recognizing textual entailment
For example, such a system trained in the news domain may learn that a sentence like {``}Palestinians recognize Texas as part of Mexico{''} tends to be unsupported, but this fact (and its corresponding lexicalized cues) have no value in, say, a scientific domain.
Visual Supervision in Bootstrapped Information Extraction
We challenge a common assumption in active learning, that a list-based interface populated by informative samples provides for efficient and effective data annotation.
Detecting Diabetes Risk from Social Media Activity
This work explores the detection of individuals{'} risk of type 2 diabetes mellitus (T2DM) directly from their social media (Twitter) activity.
An Exploration of Three Lightly-supervised Representation Learning Approaches for Named Entity Classification
Several semi-supervised representation learning methods have been proposed recently that mitigate the drawbacks of traditional bootstrapping: they reduce the amount of semantic drift introduced by iterative approaches through one-shot learning; others address the sparsity of data through the learning of custom, dense representation for the information modeled.
Sanity Check: A Strong Alignment and Information Retrieval Baseline for Question Answering
We also achieve 26. 56\% and 58. 36\% on ARC challenge and easy dataset respectively.
Scientific Discovery as Link Prediction in Influence and Citation Graphs
We introduce a machine learning approach for the identification of {``}white spaces{''} in scientific knowledge.
Keep Your Bearings: Lightly-Supervised Information Extraction with Ladder Networks That Avoids Semantic Drift
We propose a novel approach to semi-supervised learning for information extraction that uses ladder networks (Rasmus et al., 2015).
Lightly-supervised Representation Learning with Global Interpretability
We propose a lightly-supervised approach for information extraction, in particular named entity classification, which combines the benefits of traditional bootstrapping, i. e., use of limited annotations and interpretability of extraction patterns, with the robust learning approaches proposed in representation learning.
Text Annotation Graphs: Annotating Complex Natural Language Phenomena
Additionally, we include an approach to representing text annotations in which annotation subgraphs, or semantic summaries, are used to show relationships outside of the sequential context of the text itself.
Learning what to read: Focused machine reading
In this work, we introduce a focused reading approach to guide the machine reading of biomedical literature towards what literature should be read to answer a biomedical query as efficiently as possible.
Tell Me Why: Using Question Answering as Distant Supervision for Answer Justification
We propose a neural network architecture for QA that reranks answer justifications as an intermediate (and human-interpretable) step in answer selection.
Ranked #1 on
Question Answering
on AI2 Kaggle Dataset
Framing QA as Building and Ranking Intersentence Answer Justifications
Our best configuration answers 44{\%} of the questions correctly, where the top justifications for 57{\%} of these correct answers contain a compelling human-readable justification that explains the inference required to arrive at the correct answer.
What's in an Explanation? Characterizing Knowledge and Inference Requirements for Elementary Science Exams
These explanations are used to create a fine-grained categorization of the requirements.
Creating Causal Embeddings for Question Answering with Minimal Supervision
We argue that a better approach is to look for answers that are related to the question in a relevant way, according to the information need of the question, which may be determined through task-specific embeddings.
SnapToGrid: From Statistical to Interpretable Models for Biomedical Information Extraction
We propose an approach for biomedical information extraction that marries the advantages of machine learning models, e. g., learning directly from data, with the benefits of rule-based approaches, e. g., interpretability.
This before That: Causal Precedence in the Biomedical Domain
Causal precedence between biochemical interactions is crucial in the biomedical domain, because it transforms collections of individual interactions, e. g., bindings and phosphorylations, into the causal mechanisms needed to inform meaningful search and inference.
Odin's Runes: A Rule Language for Information Extraction
Odin is an information extraction framework that applies cascades of finite state automata over both surface text and syntactic dependency graphs.
Towards using social media to identify individuals at risk for preventable chronic illness
The strategy uses a game-like quiz with data and questions acquired semi-automatically from Twitter.
Sieve-based Coreference Resolution in the Biomedical Domain
We describe challenges and advantages unique to coreference resolution in the biomedical domain, and a sieve-based architecture that leverages domain knowledge for both entity and event coreference resolution.
Description of the Odin Event Extraction Framework and Rule Language
Here we include a thorough definition of the Odin rule language, together with a description of the Odin API in the Scala language, which allows one to apply these rules to arbitrary texts.
Higher-order Lexical Semantic Models for Non-factoid Answer Reranking
We introduce a higher-order formalism that allows all these lexical semantic models to chain direct evidence to construct indirect associations between question and answer texts, by casting the task as the traversal of graphs that encode direct term associations.
Analyzing the Language of Food on Social Media
We investigate the predictive power behind the language of food on social media.
On the Importance of Text Analysis for Stock Price Prediction
We investigate the importance of text analysis for stock price prediction.
Event Extraction Using Distant Supervision
We present a new publicly available dataset and event extraction task in the plane crash domain based on Wikipedia infoboxes and newswire text.
