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.
1 code implementation • 18 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.
no code implementations • 17 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.
1 code implementation • 10 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.
1 code implementation • 19 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.
1 code implementation • 15 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.
no code implementations • 11 Apr 2022 • Vishal Sunder, Eric Fosler-Lussier, Samuel Thomas, Hong-Kwang J. Kuo, Brian Kingsbury
Recent advances in End-to-End (E2E) Spoken Language Understanding (SLU) have been primarily due to effective pretraining of speech representations.
no code implementations • 11 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
no code implementations • 11 Apr 2022 • Vishal Sunder, Samuel Thomas, Hong-Kwang J. Kuo, Jatin Ganhotra, Brian Kingsbury, Eric Fosler-Lussier
In the absence of gold transcripts to fine-tune an ASR model, our model outperforms this baseline by a significant margin of 10% absolute F1 score.
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.
no code implementations • 23 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
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.
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.
1 code implementation • 27 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.
1 code implementation • 28 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.
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.
1 code implementation • 3 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.
no code implementations • 3 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.
no code implementations • 11 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.
no code implementations • 18 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.
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.
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.
2 code implementations • WS 2019 • Brendan Whitaker, Denis Newman-Griffis, Aparajita Haldar, Hakan Ferhatosmanoglu, Eric Fosler-Lussier
Analysis of word embedding properties to inform their use in downstream NLP tasks has largely been studied by assessing nearest neighbors.
1 code implementation • 25 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
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.
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.
no code implementations • 26 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.
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.
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.
1 code implementation • 23 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.
no code implementations • 13 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.
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.