Search Results for author: Brendan O{'}Connor

Found 13 papers, 1 papers with code

Query-focused Sentence Compression in Linear Time

no code implementations IJCNLP 2019 H, Abram ler, Brendan O{'}Connor

Search applications often display shortened sentences which must contain certain query terms and must fit within the space constraints of a user interface.

Sentence Compression

Summarizing Relationships for Interactive Concept Map Browsers

no code implementations WS 2019 H, Abram ler, Premkumar Ganeshkumar, Brendan O{'}Connor, Mohamed Altantawy

We present a model which responds to such queries by returning one or more short, importance-ranked, natural language descriptions of the relationship between two requested concepts, for display in a visual interface.

Evaluating Grammaticality in Seq2seq Models with a Broad Coverage HPSG Grammar: A Case Study on Machine Translation

no code implementations WS 2018 Johnny Wei, Khiem Pham, Brendan O{'}Connor, Brian Dillon

We explore whether such output belongs to a formal and realistic grammar, by employing the English Resource Grammar (ERG), a broad coverage, linguistically precise HPSG-based grammar of English.

Machine Translation Translation

Uncertainty-aware generative models for inferring document class prevalence

1 code implementation EMNLP 2018 Katherine Keith, Brendan O{'}Connor

Prevalence estimation is the task of inferring the relative frequency of classes of unlabeled examples in a group{---}for example, the proportion of a document collection with positive sentiment.

Bayesian Inference Epidemiology

Twitter Universal Dependency Parsing for African-American and Mainstream American English

no code implementations ACL 2018 Su Lin Blodgett, Johnny Wei, Brendan O{'}Connor

Due to the presence of both Twitter-specific conventions and non-standard and dialectal language, Twitter presents a significant parsing challenge to current dependency parsing tools.

Dependency Parsing Information Retrieval +3

Relational Summarization for Corpus Analysis

no code implementations NAACL 2018 H, Abram ler, Brendan O{'}Connor

This work introduces a new problem, relational summarization, in which the goal is to generate a natural language summary of the relationship between two lexical items in a corpus, without reference to a knowledge base.

Relation Extraction

A Dataset and Classifier for Recognizing Social Media English

no code implementations WS 2017 Su Lin Blodgett, Johnny Wei, Brendan O{'}Connor

While language identification works well on standard texts, it performs much worse on social media language, in particular dialectal language{---}even for English.

Language Identification Language Modelling

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