Search Results for author: Vivek Srikumar

Found 60 papers, 21 papers with code

Sprucing up Supersenses: Untangling the Semantic Clusters of Accompaniment and Purpose

no code implementations COLING (LAW) 2020 Jena D. Hwang, Nathan Schneider, Vivek Srikumar

We reevaluate an existing adpositional annotation scheme with respect to two thorny semantic domains: accompaniment and purpose.

Putting Words in BERT’s Mouth: Navigating Contextualized Vector Spaces with Pseudowords

1 code implementation EMNLP 2021 Taelin Karidi, Yichu Zhou, Nathan Schneider, Omri Abend, Vivek Srikumar

We present a method for exploring regions around individual points in a contextualized vector space (particularly, BERT space), as a way to investigate how these regions correspond to word senses.

Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords

no code implementations23 Sep 2021 Taelin Karidi, Yichu Zhou, Nathan Schneider, Omri Abend, Vivek Srikumar

We present a method for exploring regions around individual points in a contextualized vector space (particularly, BERT space), as a way to investigate how these regions correspond to word senses.

Is My Model Using The Right Evidence? Systematic Probes for Examining Evidence-Based Tabular Reasoning

no code implementations2 Aug 2021 Vivek Gupta, Riyaz A. Bhat, Atreya Ghosal, Manish Srivastava, Maneesh Singh, Vivek Srikumar

Our experiments demonstrate that a BERT-based model representative of today's state-of-the-art fails to properly reason on the following counts: it often (a) misses the relevant evidence, (b) suffers from hypothesis and knowledge biases, and, (c) relies on annotation artifacts and knowledge from pre-trained language models as primary evidence rather than relying on reasoning on the premises in the tabular input.

Language Modelling

Evaluating Relaxations of Logic for Neural Networks: A Comprehensive Study

1 code implementation28 Jul 2021 Mattia Medina Grespan, Ashim Gupta, Vivek Srikumar

Symbolic knowledge can provide crucial inductive bias for training neural models, especially in low data regimes.


A Closer Look at How Fine-tuning Changes BERT

no code implementations27 Jun 2021 Yichu Zhou, Vivek Srikumar

However, how fine-tuning for a task changes the underlying space is less studied.


X-FACT: A New Benchmark Dataset for Multilingual Fact Checking

no code implementations ACL 2021 Ashim Gupta, Vivek Srikumar

In this work, we introduce X-FACT: the largest publicly available multilingual dataset for factual verification of naturally existing real-world claims.

Domain Generalization Fact Checking

Database Workload Characterization with Query Plan Encoders

1 code implementation26 May 2021 Debjyoti Paul, Jie Cao, Feifei Li, Vivek Srikumar

To address this workload characterization problem, we propose our query plan encoders that learn essential features and their correlations from query plans.

Representation Learning Transfer Learning

DirectProbe: Studying Representations without Classifiers

1 code implementation NAACL 2021 Yichu Zhou, Vivek Srikumar

Understanding how linguistic structures are encoded in contextualized embedding could help explain their impressive performance across NLP@.

Incorporating External Knowledge to Enhance Tabular Reasoning

1 code implementation NAACL 2021 J. Neeraja, Vivek Gupta, Vivek Srikumar

Reasoning about tabular information presents unique challenges to modern NLP approaches which largely rely on pre-trained contextualized embeddings of text.

Natural Language Inference

VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations

1 code implementation6 Apr 2021 Archit Rathore, Sunipa Dev, Jeff M. Phillips, Vivek Srikumar, Yan Zheng, Chin-Chia Michael Yeh, Junpeng Wang, Wei zhang, Bei Wang

To aid this, we present Visualization of Embedding Representations for deBiasing system ("VERB"), an open-source web-based visualization tool that helps the users gain a technical understanding and visual intuition of the inner workings of debiasing techniques, with a focus on their geometric properties.

Decision Making Dimensionality Reduction +2

BERT & Family Eat Word Salad: Experiments with Text Understanding

1 code implementation10 Jan 2021 Ashim Gupta, Giorgi Kvernadze, Vivek Srikumar

In this paper, we study the response of large models from the BERT family to incoherent inputs that should confuse any model that claims to understand natural language.

Supertagging the Long Tail with Tree-Structured Decoding of Complex Categories

1 code implementation2 Dec 2020 Jakob Prange, Nathan Schneider, Vivek Srikumar

Our best tagger is capable of recovering a sizeable fraction of the long-tail supertags and even generates CCG categories that have never been seen in training, while approximating the prior state of the art in overall tag accuracy with fewer parameters.

Structured Prediction

UnQovering Stereotyping Biases via Underspecified Questions

1 code implementation Findings of the Association for Computational Linguistics 2020 Tao Li, Tushar Khot, Daniel Khashabi, Ashish Sabharwal, Vivek Srikumar

Our broad study reveals that (1) all these models, with and without fine-tuning, have notable stereotyping biases in these classes; (2) larger models often have higher bias; and (3) the effect of fine-tuning on bias varies strongly with the dataset and the model size.

Fine-tuning Question Answering

A Simple Global Neural Discourse Parser

no code implementations2 Sep 2020 Yichu Zhou, Omri Koshorek, Vivek Srikumar, Jonathan Berant

Discourse parsing is largely dominated by greedy parsers with manually-designed features, while global parsing is rare due to its computational expense.

Discourse Parsing

OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings

1 code implementation EMNLP 2021 Sunipa Dev, Tao Li, Jeff M. Phillips, Vivek Srikumar

Language representations are known to carry stereotypical biases and, as a result, lead to biased predictions in downstream tasks.

Rectification Word Embeddings

Learning Constraints for Structured Prediction Using Rectifier Networks

1 code implementation ACL 2020 Xingyuan Pan, Maitrey Mehta, Vivek Srikumar

Various natural language processing tasks are structured prediction problems where outputs are constructed with multiple interdependent decisions.

Structured Prediction

INFOTABS: Inference on Tables as Semi-structured Data

no code implementations ACL 2020 Vivek Gupta, Maitrey Mehta, Pegah Nokhiz, Vivek Srikumar

In this paper, we observe that semi-structured tabulated text is ubiquitous; understanding them requires not only comprehending the meaning of text fragments, but also implicit relationships between them.

Structured Tuning for Semantic Role Labeling

1 code implementation ACL 2020 Tao Li, Parth Anand Jawale, Martha Palmer, Vivek Srikumar

We start with a strong baseline (RoBERTa) to validate the impact of our approach, and show that our framework outperforms the baseline by learning to comply with declarative constraints.

Semantic Role Labeling

Amazon at MRP 2019: Parsing Meaning Representations with Lexical and Phrasal Anchoring

no code implementations CONLL 2019 Jie Cao, Yi Zhang, Adel Youssef, Vivek Srikumar

This paper describes the system submission of our team Amazon to the shared task on Cross Framework Meaning Representation Parsing (MRP) at the 2019 Conference for Computational Language Learning (CoNLL).

A Logic-Driven Framework for Consistency of Neural Models

1 code implementation IJCNLP 2019 Tao Li, Vivek Gupta, Maitrey Mehta, Vivek Srikumar

While neural models show remarkable accuracy on individual predictions, their internal beliefs can be inconsistent across examples.

Natural Language Inference

On Measuring and Mitigating Biased Inferences of Word Embeddings

1 code implementation25 Aug 2019 Sunipa Dev, Tao Li, Jeff Phillips, Vivek Srikumar

Word embeddings carry stereotypical connotations from the text they are trained on, which can lead to invalid inferences in downstream models that rely on them.

Natural Language Inference Word Embeddings

Preparing SNACS for Subjects and Objects

1 code implementation WS 2019 Adi Shalev, Jena D. Hwang, Nathan Schneider, Vivek Srikumar, Omri Abend, Ari Rappoport

Research on adpositions and possessives in multiple languages has led to a small inventory of general-purpose meaning classes that disambiguate tokens.

Observing Dialogue in Therapy: Categorizing and Forecasting Behavioral Codes

1 code implementation ACL 2019 Jie Cao, Michael Tanana, Zac E. Imel, Eric Poitras, David C. Atkins, Vivek Srikumar

Specifically, we address the problem of providing real-time guidance to therapists with a dialogue observer that (1) categorizes therapist and client MI behavioral codes and, (2) forecasts codes for upcoming utterances to help guide the conversation and potentially alert the therapist.

Augmenting Neural Networks with First-order Logic

1 code implementation ACL 2019 Tao Li, Vivek Srikumar

Today, the dominant paradigm for training neural networks involves minimizing task loss on a large dataset.

Chunking Natural Language Inference +1

Learning In Practice: Reasoning About Quantization

no code implementations27 May 2019 Annie Cherkaev, Waiming Tai, Jeff Phillips, Vivek Srikumar

There is a mismatch between the standard theoretical analyses of statistical machine learning and how learning is used in practice.


Visual Interrogation of Attention-Based Models for Natural Language Inference and Machine Comprehension

no code implementations EMNLP 2018 Shusen Liu, Tao Li, Zhimin Li, Vivek Srikumar, Valerio Pascucci, Peer-Timo Bremer

Neural networks models have gained unprecedented popularity in natural language processing due to their state-of-the-art performance and the flexible end-to-end training scheme.

Decision Making Natural Language Inference +1

Learning to Speed Up Structured Output Prediction

no code implementations ICML 2018 Xingyuan Pan, Vivek Srikumar

Predicting structured outputs can be computationally onerous due to the combinatorially large output spaces.

Relation Extraction

Comprehensive Supersense Disambiguation of English Prepositions and Possessives

1 code implementation ACL 2018 Nathan Schneider, Jena D. Hwang, Vivek Srikumar, Jakob Prange, Austin Blodgett, Sarah R. Moeller, Aviram Stern, Adi Bitan, Omri Abend

Semantic relations are often signaled with prepositional or possessive marking--but extreme polysemy bedevils their analysis and automatic interpretation.

Double Trouble: The Problem of Construal in Semantic Annotation of Adpositions

no code implementations SEMEVAL 2017 Jena D. Hwang, Archna Bhatia, Na-Rae Han, Tim O{'}Gorman, Vivek Srikumar, Nathan Schneider

We consider the semantics of prepositions, revisiting a broad-coverage annotation scheme used for annotating all 4, 250 preposition tokens in a 55, 000 word corpus of English.

An Algebra for Feature Extraction

no code implementations ACL 2017 Vivek Srikumar

Though feature extraction is a necessary first step in statistical NLP, it is often seen as a mere preprocessing step.

Chunking Relation Extraction

Adposition and Case Supersenses v2.5: Guidelines for English

2 code implementations7 Apr 2017 Nathan Schneider, Jena D. Hwang, Archna Bhatia, Vivek Srikumar, Na-Rae Han, Tim O'Gorman, Sarah R. Moeller, Omri Abend, Adi Shalev, Austin Blodgett, Jakob Prange

This document offers a detailed linguistic description of SNACS (Semantic Network of Adposition and Case Supersenses; Schneider et al., 2018), an inventory of 50 semantic labels ("supersenses") that characterize the use of adpositions and case markers at a somewhat coarse level of granularity, as demonstrated in the STREUSLE corpus (https://github. com/nert-gu/streusle/; version 4. 3 tracks guidelines version 2. 5).

Integer Linear Programming formulations in Natural Language Processing

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.

Dependency Parsing Natural Language Inference +4

Coping with Construals in Broad-Coverage Semantic Annotation of Adpositions

no code implementations10 Mar 2017 Jena D. Hwang, Archna Bhatia, Na-Rae Han, Tim O'Gorman, Vivek Srikumar, Nathan Schneider

We consider the semantics of prepositions, revisiting a broad-coverage annotation scheme used for annotating all 4, 250 preposition tokens in a 55, 000 word corpus of English.

A corpus of preposition supersenses in English web reviews

no code implementations8 May 2016 Nathan Schneider, Jena D. Hwang, Vivek Srikumar, Meredith Green, Kathryn Conger, Tim O'Gorman, Martha Palmer

We present the first corpus annotated with preposition supersenses, unlexicalized categories for semantic functions that can be marked by English prepositions (Schneider et al., 2015).

EDISON: Feature Extraction for NLP, Simplified

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.

Expressiveness of Rectifier Networks

no code implementations18 Nov 2015 Xingyuan Pan, Vivek Srikumar

However, unlike threshold and sigmoid networks, ReLU networks are less explored from the perspective of their expressiveness.

Learning Distributed Representations for Structured Output Prediction

no code implementations NeurIPS 2014 Vivek Srikumar, Christopher D. Manning

In recent years, distributed representations of inputs have led to performance gains in many applications by allowing statistical information to be shared across inputs.

Document Classification Part-Of-Speech Tagging +1

An Inventory of Preposition Relations

no code implementations24 May 2013 Vivek Srikumar, Dan Roth

We describe an inventory of semantic relations that are expressed by prepositions.

Word Sense Disambiguation

Modeling Semantic Relations Expressed by Prepositions

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.

Natural Language Inference Question Answering +1

An NLP Curator (or: How I Learned to Stop Worrying and Love NLP Pipelines)

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.

Cannot find the paper you are looking for? You can Submit a new open access paper.