papers

Publications (28)

cs.LG2019

A Causality-Guided Prediction of the TED Talk Ratings from the Speech-Transcripts using Neural Networks

Md Iftekhar Tanveer, Md Kamrul Hasan, Daniel Gildea +1

Automated prediction of public speaking performance enables novel systems for tutoring public speaking skills. We use the largest open repository---TED Talks---to predict the ratin…

cs.CL2015

Feature-based Decipherment for Large Vocabulary Machine Translation

Iftekhar Naim, Daniel Gildea

Orthographic similarities across languages provide a strong signal for probabilistic decipherment, especially for closely related language pairs. The existing decipherment models,…

cs.CL2019

Leveraging Dependency Forest for Neural Medical Relation Extraction

Linfeng Song, Yue Zhang, Daniel Gildea +3

Medical relation extraction discovers relations between entity mentions in text, such as research articles. For this task, dependency syntax has been recognized as a crucial source…

cs.CL2018

Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks

Linfeng Song, Zhiguo Wang, Mo Yu +3

Multi-hop reading comprehension focuses on one type of factoid question, where a system needs to properly integrate multiple pieces of evidence to correctly answer a question. Prev…

cs.CL2018

A Graph-to-Sequence Model for AMR-to-Text Generation

Linfeng Song, Yue Zhang, Zhiguo Wang +1

The problem of AMR-to-text generation is to recover a text representing the same meaning as an input AMR graph. The current state-of-the-art method uses a sequence-to-sequence mode…

cs.CL2022

Strictly Breadth-First AMR Parsing

Chen Yu, Daniel Gildea

AMR parsing is the task that maps a sentence to an AMR semantic graph automatically. We focus on the breadth-first strategy of this task, which was proposed recently and achieved b…

cs.CL2021

Latent Tree Decomposition Parsers for AMR-to-Text Generation

Lisa Jin, Daniel Gildea

Graph encoders in AMR-to-text generation models often rely on neighborhood convolutions or global vertex attention. While these approaches apply to general graphs, AMRs may be amen…

cs.CL2019

AMR-to-Text Generation with Cache Transition Systems

Lisa Jin, Daniel Gildea

Text generation from AMR involves emitting sentences that reflect the meaning of their AMR annotations. Neural sequence-to-sequence models have successfully been used to decode str…

cs.CL2017

Addressing the Data Sparsity Issue in Neural AMR Parsing

Xiaochang Peng, Chuan Wang, Daniel Gildea +1

Neural attention models have achieved great success in different NLP tasks. How- ever, they have not fulfilled their promise on the AMR parsing task due to the data sparsity issue.…

cs.MM2019

Predicting TED Talk Ratings from Language and Prosody

Md Iftekhar Tanveer, Md Kamrul Hassan, Daniel Gildea +1

We use the largest open repository of public speaking---TED Talks---to predict the ratings of the online viewers. Our dataset contains over 2200 TED Talk transcripts (includes over…

cs.CL2021

Tree Decomposition Attention for AMR-to-Text Generation

Lisa Jin, Daniel Gildea

Text generation from AMR requires mapping a semantic graph to a string that it annotates. Transformer-based graph encoders, however, poorly capture vertex dependencies that may ben…

cs.CL2019

SemBleu: A Robust Metric for AMR Parsing Evaluation

Linfeng Song, Daniel Gildea

Evaluating AMR parsing accuracy involves comparing pairs of AMR graphs. The major evaluation metric, SMATCH (Cai and Knight, 2013), searches for one-to-one mappings between the nod…

cs.CL2018

Neural Transition-based Syntactic Linearization

Linfeng Song, Yue Zhang, Daniel Gildea

The task of linearization is to find a grammatical order given a set of words. Traditional models use statistical methods. Syntactic linearization systems, which generate a sentenc…

cs.CL2020

Unsupervised Bilingual Lexicon Induction Across Writing Systems

Parker Riley, Daniel Gildea

Recent embedding-based methods in unsupervised bilingual lexicon induction have shown good results, but generally have not leveraged orthographic (spelling) information, which can…

cs.CL2017

AMR-to-text Generation with Synchronous Node Replacement Grammar

Linfeng Song, Xiaochang Peng, Yue Zhang +2

This paper addresses the task of AMR-to-text generation by leveraging synchronous node replacement grammar. During training, graph-to-string rules are learned using a heuristic ext…

cs.CL2016

Parsing Linear Context-Free Rewriting Systems with Fast Matrix Multiplication

Shay B. Cohen, Daniel Gildea

We describe a matrix multiplication recognition algorithm for a subset of binary linear context-free rewriting systems (LCFRS) with running time where

cs.CL2016

Exploring phrase-compositionality in skip-gram models

Xiaochang Peng, Daniel Gildea

In this paper, we introduce a variation of the skip-gram model which jointly learns distributed word vector representations and their way of composing to form phrase embeddings. In…

cs.LG2012

Convergence of the EM Algorithm for Gaussian Mixtures with Unbalanced Mixing Coefficients

Iftekhar Naim, Daniel Gildea

The speed of convergence of the Expectation Maximization (EM) algorithm for Gaussian mixture model fitting is known to be dependent on the amount of overlap among the mixture compo…

cs.CL2018

N-ary Relation Extraction using Graph State LSTM

Linfeng Song, Yue Zhang, Zhiguo Wang +1

Cross-sentence -ary relation extraction detects relations among entities across multiple sentences. Typical methods formulate an input as a \textit{document graph}, integrat…

cs.FL2013

Synchronous Context-Free Grammars and Optimal Linear Parsing Strategies

Pierluigi Crescenzi, Daniel Gildea, Andrea Marino +2

Synchronous Context-Free Grammars (SCFGs), also known as syntax-directed translation schemata, are unlike context-free grammars in that they do not have a binary normal form. In ge…

cs.CL2019

Semantic Neural Machine Translation using AMR

Linfeng Song, Daniel Gildea, Yue Zhang +2

It is intuitive that semantic representations can be useful for machine translation, mainly because they can help in enforcing meaning preservation and handling data sparsity (many…

cs.CL2016

Sense Embedding Learning for Word Sense Induction

Linfeng Song, Zhiguo Wang, Haitao Mi +1

Conventional word sense induction (WSI) methods usually represent each instance with discrete linguistic features or cooccurrence features, and train a model for each polysemous wo…

cs.CL2020

Tensors over Semirings for Latent-Variable Weighted Logic Programs

Esma Balkir, Daniel Gildea, Shay Cohen

Semiring parsing is an elegant framework for describing parsers by using semiring weighted logic programs. In this paper we present a generalization of this concept: latent-variabl…

cs.HC2015

Automated Analysis and Prediction of Job Interview Performance

Iftekhar Naim, M. Iftekhar Tanveer, Daniel Gildea +2

We present a computational framework for automatically quantifying verbal and nonverbal behaviors in the context of job interviews. The proposed framework is trained by analyzing t…

cs.DS2020

AWLCO: All-Window Length Co-Occurrence

Joshua Sobel, Noah Bertram, Chen Ding +2

Analyzing patterns in a sequence of events has applications in text analysis, computer programming, and genomics research. In this paper, we consider the all-window-length analysis…

cs.CL2016

AMR-to-text generation as a Traveling Salesman Problem

Linfeng Song, Yue Zhang, Xiaochang Peng +2

The task of AMR-to-text generation is to generate grammatical text that sustains the semantic meaning for a given AMR graph. We at- tack the task by first partitioning the AMR grap…

cs.CL2022

Hierarchical Context Tagging for Utterance Rewriting

Lisa Jin, Linfeng Song, Lifeng Jin +2

Utterance rewriting aims to recover coreferences and omitted information from the latest turn of a multi-turn dialogue. Recently, methods that tag rather than linearly generate seq…

cs.CL2015

Human languages order information efficiently

Daniel Gildea, T. Florian Jaeger

Most languages use the relative order between words to encode meaning relations. Languages differ, however, in what orders they use and how these orders are mapped onto different m…