Search Results for author: Eric Fosler-Lussier

Found 44 papers, 14 papers with code

How Self-Attention Improves Rare Class Performance in a Question-Answering Dialogue Agent

no code implementations SIGDIAL (ACL) 2020 Adam Stiff, Qi Song, Eric Fosler-Lussier

Contextualized language modeling using deep Transformer networks has been applied to a variety of natural language processing tasks with remarkable success.

Language Modelling Question Answering +1

A Multi-Aspect Framework for Counter Narrative Evaluation using Large Language Models

1 code implementation18 Feb 2024 Jaylen Jones, Lingbo Mo, Eric Fosler-Lussier, Huan Sun

Counter narratives - informed responses to hate speech contexts designed to refute hateful claims and de-escalate encounters - have emerged as an effective hate speech intervention strategy.

End-to-End real time tracking of children's reading with pointer network

no code implementations17 Oct 2023 Vishal Sunder, Beulah Karrolla, Eric Fosler-Lussier

To train this pointer network, we generate ground truth training signals by using forced alignment between the read speech and the text being read on the training set.

Selective Demonstrations for Cross-domain Text-to-SQL

1 code implementation10 Oct 2023 Shuaichen Chang, Eric Fosler-Lussier

Large language models (LLMs) with in-context learning have demonstrated impressive generalization capabilities in the cross-domain text-to-SQL task, without the use of in-domain annotations.

In-Context Learning Text-To-SQL

How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settings

1 code implementation19 May 2023 Shuaichen Chang, Eric Fosler-Lussier

Large language models (LLMs) with in-context learning have demonstrated remarkable capability in the text-to-SQL task.

In-Context Learning Retrieval +1

MapQA: A Dataset for Question Answering on Choropleth Maps

1 code implementation15 Nov 2022 Shuaichen Chang, David Palzer, Jialin Li, Eric Fosler-Lussier, Ningchuan Xiao

Our experimental results show that V-MODEQA has better overall performance and robustness on MapQA than the state-of-the-art ChartQA and VQA algorithms by capturing the unique properties in map question answering.

Question Answering Visual Question Answering

Building an ASR Error Robust Spoken Virtual Patient System in a Highly Class-Imbalanced Scenario Without Speech Data

no code implementations11 Apr 2022 Vishal Sunder, Prashant Serai, Eric Fosler-Lussier

As it is difficult to collect spoken data from users without a functioning SLU system, our method does not rely on spoken data for training, rather we use an ASR error predictor to "speechify" the text data.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Learning Latent Structures for Cross Action Phrase Relations in Wet Lab Protocols

no code implementations ACL 2021 Chaitanya Kulkarni, Jany Chan, Eric Fosler-Lussier, Raghu Machiraju

We propose a new model that incrementally learns latent structures and is better suited to resolving inter-sentence relations and implicit arguments.


Hallucination of speech recognition errors with sequence to sequence learning

no code implementations23 Mar 2021 Prashant Serai, Vishal Sunder, Eric Fosler-Lussier

Automatic Speech Recognition (ASR) is an imperfect process that results in certain mismatches in ASR output text when compared to plain written text or transcriptions.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

TextEssence: A Tool for Interactive Analysis of Semantic Shifts Between Corpora

1 code implementation NAACL 2021 Denis Newman-Griffis, Venkatesh Sivaraman, Adam Perer, Eric Fosler-Lussier, Harry Hochheiser

Embeddings of words and concepts capture syntactic and semantic regularities of language; however, they have seen limited use as tools to study characteristics of different corpora and how they relate to one another.

Contextualized Embeddings for Enriching Linguistic Analyses on Politeness

no code implementations COLING 2020 Ahmad Aljanaideh, Eric Fosler-Lussier, Marie-Catherine de Marneffe

In this work, we introduce a model which leverages the pre-trained BERT model to cluster contextualized representations of a word based on (1) the context in which the word appears and (2) the labels of items the word occurs in.

Clustering Word Embeddings

Automated Coding of Under-Studied Medical Concept Domains: Linking Physical Activity Reports to the International Classification of Functioning, Disability, and Health

1 code implementation27 Nov 2020 Denis Newman-Griffis, Eric Fosler-Lussier

Both classification and candidate selection approaches present distinct strengths for automated coding in under-studied domains, and we highlight that the combination of (i) a small annotated data set; (ii) expert definitions of codes of interest; and (iii) a representative text corpus is sufficient to produce high-performing automated coding systems.

Language Modelling

Handling Class Imbalance in Low-Resource Dialogue Systems by Combining Few-Shot Classification and Interpolation

1 code implementation28 Oct 2020 Vishal Sunder, Eric Fosler-Lussier

Utterance classification performance in low-resource dialogue systems is constrained by an inevitably high degree of data imbalance in class labels.

Classification Dialogue Act Classification +1

Sequence-to-Set Semantic Tagging for Complex Query Reformulation and Automated Text Categorization in Biomedical IR using Self-Attention

no code implementations WS 2020 Manirupa Das, Juanxi Li, Eric Fosler-Lussier, Simon Lin, Steve Rust, Yungui Huang, Rajiv Ramnath

Novel contexts, comprising a set of terms referring to one or more concepts, may often arise in complex querying scenarios such as in evidence-based medicine (EBM) involving biomedical literature.

Retrieval Text Categorization

Phonetic Feedback for Speech Enhancement With and Without Parallel Speech Data

1 code implementation3 Mar 2020 Peter Plantinga, Deblin Bagchi, Eric Fosler-Lussier

While deep learning systems have gained significant ground in speech enhancement research, these systems have yet to make use of the full potential of deep learning systems to provide high-level feedback.

Speech Enhancement

Towards Real-time Mispronunciation Detection in Kids' Speech

no code implementations3 Mar 2020 Peter Plantinga, Eric Fosler-Lussier

The other loss term uses a uni-directional model as teacher model to align the bi-directional model.

Sequence-to-Set Semantic Tagging: End-to-End Multi-label Prediction using Neural Attention for Complex Query Reformulation and Automated Text Categorization

no code implementations11 Nov 2019 Manirupa Das, Juanxi Li, Eric Fosler-Lussier, Simon Lin, Soheil Moosavinasab, Steve Rust, Yungui Huang, Rajiv Ramnath

Our approach to generate document encodings employing our sequence-to-set models for inference of semantic tags, gives to the best of our knowledge, the state-of-the-art for both, the unsupervised query expansion task for the TREC CDS 2016 challenge dataset when evaluated on an Okapi BM25--based document retrieval system; and also over the MLTM baseline (Soleimani et al, 2016), for both supervised and semi-supervised multi-label prediction tasks on the del. icio. us and Ohsumed datasets.

Multi-Label Classification Retrieval +1

Learning to Answer Subjective, Specific Product-Related Queries using Customer Reviews by Adversarial Domain Adaptation

no code implementations18 Oct 2019 Manirupa Das, Zhen Wang, Evan Jaffe, Madhuja Chattopadhyay, Eric Fosler-Lussier, Rajiv Ramnath

Online customer reviews on large-scale e-commerce websites, represent a rich and varied source of opinion data, often providing subjective qualitative assessments of product usage that can help potential customers to discover features that meet their personal needs and preferences.

Domain Adaptation Sentence

Writing habits and telltale neighbors: analyzing clinical concept usage patterns with sublanguage embeddings

no code implementations WS 2019 Denis Newman-Griffis, Eric Fosler-Lussier

Natural language processing techniques are being applied to increasingly diverse types of electronic health records, and can benefit from in-depth understanding of the distinguishing characteristics of medical document types.

HARE: a Flexible Highlighting Annotator for Ranking and Exploration

1 code implementation IJCNLP 2019 Denis Newman-Griffis, Eric Fosler-Lussier

Exploration and analysis of potential data sources is a significant challenge in the application of NLP techniques to novel information domains.

Document Ranking

An Exploration of Mimic Architectures for Residual Network Based Spectral Mapping

1 code implementation25 Sep 2018 Peter Plantinga, Deblin Bagchi, Eric Fosler-Lussier

Spectral mapping uses a deep neural network (DNN) to map directly from noisy speech to clean speech.

Sound Audio and Speech Processing

Jointly Embedding Entities and Text with Distant Supervision

2 code implementations WS 2018 Denis Newman-Griffis, Albert M. Lai, Eric Fosler-Lussier

Learning representations for knowledge base entities and concepts is becoming increasingly important for NLP applications.

Phrase2VecGLM: Neural generalized language model--based semantic tagging for complex query reformulation in medical IR

no code implementations WS 2018 Manirupa Das, Eric Fosler-Lussier, Simon Lin, Soheil Moosavinasab, David Chen, Steve Rust, Yungui Huang, Rajiv Ramnath

In this work, we develop a novel, completely unsupervised, neural language model-based document ranking approach to semantic tagging of documents, using the document to be tagged as a query into the GLM to retrieve candidate phrases from top-ranked related documents, thus associating every document with novel related concepts extracted from the text.

Document Ranking Information Retrieval +4

Spectral feature mapping with mimic loss for robust speech recognition

no code implementations26 Mar 2018 Deblin Bagchi, Peter Plantinga, Adam Stiff, Eric Fosler-Lussier

For the task of speech enhancement, local learning objectives are agnostic to phonetic structures helpful for speech recognition.

Robust Speech Recognition Speech Enhancement +1

Cross-Lingual Transfer Learning for POS Tagging without Cross-Lingual Resources

no code implementations EMNLP 2017 Joo-Kyung Kim, Young-Bum Kim, Ruhi Sarikaya, Eric Fosler-Lussier

Evaluating on POS datasets from 14 languages in the Universal Dependencies corpus, we show that the proposed transfer learning model improves the POS tagging performance of the target languages without exploiting any linguistic knowledge between the source language and the target language.

Cross-Lingual Transfer Language Modelling +7

Insights into Analogy Completion from the Biomedical Domain

1 code implementation WS 2017 Denis Newman-Griffis, Albert M. Lai, Eric Fosler-Lussier

Analogy completion has been a popular task in recent years for evaluating the semantic properties of word embeddings, but the standard methodology makes a number of assumptions about analogies that do not always hold, either in recent benchmark datasets or when expanding into other domains.

Word Embeddings

Second-Order Word Embeddings from Nearest Neighbor Topological Features

1 code implementation23 May 2017 Denis Newman-Griffis, Eric Fosler-Lussier

We introduce second-order vector representations of words, induced from nearest neighborhood topological features in pre-trained contextual word embeddings.

named-entity-recognition Named Entity Recognition +4

How essential are unstructured clinical narratives and information fusion to clinical trial recruitment?

no code implementations13 Feb 2015 Preethi Raghavan, James L. Chen, Eric Fosler-Lussier, Albert M. Lai

We perform an empirical study to validate the argument and show that structured data alone is insufficient in resolving eligibility criteria for recruiting patients onto clinical trials for chronic lymphocytic leukemia (CLL) and prostate cancer.

Associative and Semantic Features Extracted From Web-Harvested Corpora

no code implementations LREC 2012 Elias Iosif, Maria Giannoudaki, Eric Fosler-Lussier, Alex Potamianos, ros

We address the problem of automatic classification of associative and semantic relations between words, and particularly those that hold between nouns.

Classification General Classification +5

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