Natural language research announcements

[Yonatan Bisk <bisk1 AT illinois.edu>]

The following talk will be this Friday in the Linguistics department but potentially of interest to many of us.

Adam Lopez, Johns Hopkins University (talk: Feb. 7th at 4pm in Lucy Ellis Lounge (FLB 1080))

Title: A Linguistically-Informed Formal Model of Translation

Speaker: Adam Lopez, Assistant Research Professor, Johns Hopkins University

Time: Friday, Feb. 7th, 4-5:30pm

Location: Lucy Ellis Lounge (FLB 1080)

Statistical machine translation has been very successful, resulting in a thriving industry highlighted by products like Google Translate. Yet translation systems still often fail to capture many linguistic phenomena, because they model translation as simple substitution and permutation of word tokens, sometimes informed by syntax. Formally, these models are probabilistic relations on regular or context-free sets, a poor fit for many of the world's languages. If we are to build translation systems that correctly capture linguistic phenomena, we must model those phenomena. Computational linguists have developed expressive mathematical models of language that exhibit high empirical coverage of annotated language data, correctly predict a variety of important linguistic phenomena in many languages, and can be processed with efficient algorithms. I will describe a new formal model of translation based on one of these formalisms, combinatory categorial grammar (CCG). CCG has many attractive properties, including a clean syntax-semantics interface. I will describe a synchronous CCG that generates a relation on sentence pairs with provably identical semantics. I will then give a solution for the crucial problem of recognition---the basis of any probabilistic translation algorithm---derived from a view of parsing as language intersection.

BIO: Adam Lopez works on problems at the intersection of computational linguistics, formal language theory, machine learning, and algorithms with applications to problems in natural language processing, particularly machine translation. He is an assistant research professor at Johns Hopkins University. He was previously a research fellow at the University of Edinburgh, and earned his Ph.D. at the University of Maryland.