526 citations · 1.1k across the 32 of their papers we have counts for
41 papers · 1 filter
Characterizing and Measuring Linguistic Dataset Drift
Tyler A. Chang, Kishaloy Halder, Neha Anna John +4
NLP models often degrade in performance when real world data distributions differ markedly from training data. However, existing dataset drift metrics in NLP have generally not con…
A Weak Supervision Approach for Few-Shot Aspect Based Sentiment
Robert Vacareanu, Siddharth Varia, Kishaloy Halder +5
We explore how weak supervision on abundant unlabeled data can be leveraged to improve few-shot performance in aspect-based sentiment analysis (ABSA) tasks. We propose a pipeline a…
Comparing Biases and the Impact of Multilingual Training across Multiple Languages
Sharon Levy, Neha Anna John, Ling Liu +6
Studies in bias and fairness in natural language processing have primarily examined social biases within a single language and/or across few attributes (e.g. gender, race). However…
Simple Yet Effective Synthetic Dataset Construction for Unsupervised Opinion Summarization
Ming Shen, Jie Ma, Shuai Wang +4
Opinion summarization provides an important solution for summarizing opinions expressed among a large number of reviews. However, generating aspect-specific and general summaries i…
Dynamic Benchmarking of Masked Language Models on Temporal Concept Drift with Multiple Views
Katerina Margatina, Shuai Wang, Yogarshi Vyas +3
Temporal concept drift refers to the problem of data changing over time. In NLP, that would entail that language (e.g. new expressions, meaning shifts) and factual knowledge (e.g.…
Novel Chapter Abstractive Summarization using Spinal Tree Aware Sub-Sentential Content Selection
Hardy Hardy, Miguel Ballesteros, Faisal Ladhak +3
Summarizing novel chapters is a difficult task due to the input length and the fact that sentences that appear in the desired summaries draw content from multiple places throughout…
Contrastive Training Improves Zero-Shot Classification of Semi-structured Documents
Muhammad Khalifa, Yogarshi Vyas, Shuai Wang +3
We investigate semi-structured document classification in a zero-shot setting. Classification of semi-structured documents is more challenging than that of standard unstructured do…
Instruction Tuning for Few-Shot Aspect-Based Sentiment Analysis
Siddharth Varia, Shuai Wang, Kishaloy Halder +7
Aspect-based Sentiment Analysis (ABSA) is a fine-grained sentiment analysis task which involves four elements from user-generated texts: aspect term, aspect category, opinion term,…
Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning
Vishakh Padmakumar, Leonard Lausen, Miguel Ballesteros +3
Recent work has found that multi-task training with a large number of diverse tasks can uniformly improve downstream performance on unseen target tasks. In contrast, literature on…
Label Semantics for Few Shot Named Entity Recognition
Jie Ma, Miguel Ballesteros, Srikanth Doss +4
We study the problem of few shot learning for named entity recognition. Specifically, we leverage the semantic information in the names of the labels as a way of giving the model a…
A Bag of Tricks for Dialogue Summarization
Muhammad Khalifa, Miguel Ballesteros, Kathleen McKeown
Dialogue summarization comes with its own peculiar challenges as opposed to news or scientific articles summarization. In this work, we explore four different challenges of the tas…
How much pretraining data do language models need to learn syntax?
Laura Pérez-Mayos, Miguel Ballesteros, Leo Wanner
Transformers-based pretrained language models achieve outstanding results in many well-known NLU benchmarks. However, while pretraining methods are very convenient, they are expens…
On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations
Laura Pérez-Mayos, Roberto Carlini, Miguel Ballesteros +1
The adaptation of pretrained language models to solve supervised tasks has become a baseline in NLP, and many recent works have focused on studying how linguistic information is en…
Event-Driven News Stream Clustering using Entity-Aware Contextual Embeddings
Kailash Karthik Saravanakumar, Miguel Ballesteros, Muthu Kumar Chandrasekaran +1
We propose a method for online news stream clustering that is a variant of the non-parametric streaming K-means algorithm. Our model uses a combination of sparse and dense document…
To BERT or Not to BERT: Comparing Task-specific and Task-agnostic Semi-Supervised Approaches for Sequence Tagging
Kasturi Bhattacharjee, Miguel Ballesteros, Rishita Anubhai +4
Leveraging large amounts of unlabeled data using Transformer-like architectures, like BERT, has gained popularity in recent times owing to their effectiveness in learning general r…
Linking Entities to Unseen Knowledge Bases with Arbitrary Schemas
Yogarshi Vyas, Miguel Ballesteros
In entity linking, mentions of named entities in raw text are disambiguated against a knowledge base (KB). This work focuses on linking to unseen KBs that do not have training data…
Transition-based Parsing with Stack-Transformers
Ramon Fernandez Astudillo, Miguel Ballesteros, Tahira Naseem +2
Modeling the parser state is key to good performance in transition-based parsing. Recurrent Neural Networks considerably improved the performance of transition-based systems by mod…
Structural Supervision Improves Few-Shot Learning and Syntactic Generalization in Neural Language Models
Ethan Wilcox, Peng Qian, Richard Futrell +3
Humans can learn structural properties about a word from minimal experience, and deploy their learned syntactic representations uniformly in different grammatical contexts. We asse…
Resource-Enhanced Neural Model for Event Argument Extraction
Jie Ma, Shuai Wang, Rishita Anubhai +2
Event argument extraction (EAE) aims to identify the arguments of an event and classify the roles that those arguments play. Despite great efforts made in prior work, there remain…
Severing the Edge Between Before and After: Neural Architectures for Temporal Ordering of Events
Miguel Ballesteros, Rishita Anubhai, Shuai Wang +6
In this paper, we propose a neural architecture and a set of training methods for ordering events by predicting temporal relations. Our proposed models receive a pair of events wit…
Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning
Tahira Naseem, Abhishek Shah, Hui Wan +3
Our work involves enriching the Stack-LSTM transition-based AMR parser (Ballesteros and Al-Onaizan, 2017) by augmenting training with Policy Learning and rewarding the Smatch score…
Structural Supervision Improves Learning of Non-Local Grammatical Dependencies
Ethan Wilcox, Peng Qian, Richard Futrell +2
State-of-the-art LSTM language models trained on large corpora learn sequential contingencies in impressive detail and have been shown to acquire a number of non-local grammatical…
Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State
Richard Futrell, Ethan Wilcox, Takashi Morita +3
We deploy the methods of controlled psycholinguistic experimentation to shed light on the extent to which the behavior of neural network language models reflects incremental repres…
Recursive Subtree Composition in LSTM-Based Dependency Parsing
Miryam de Lhoneux, Miguel Ballesteros, Joakim Nivre
The need for tree structure modelling on top of sequence modelling is an open issue in neural dependency parsing. We investigate the impact of adding a tree layer on top of a seque…