Author name cluster

Dekai Wu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

IJCAI Conference 2015 Conference Paper

Learning to Rap Battle with Bilingual Recursive Neural Networks

Dekai Wu
Karteek Addanki

We describe an unconventional line of attack in our quest to teach machines how to rap battle by improvising hip hop lyrics on the fly, in which a novel recursive bilingual neural network, TRAAM, implicitly learns soft, context-dependent generalizations over the structural relationships between associated parts of challenge and response raps, while avoiding the exponential complexity costs that symbolic models would require. TRAAM learns feature vectors simultaneously using context from both the challenge and the response, such that challengeresponse association patterns with similar structure tend to have similar vectors. Improvisation is modeled as a quasi-translation learning problem, where TRAAM is trained to improvise fluent and rhyming responses to challenge lyrics. The soft structural relationships learned by our TRAAM model are used to improve the probabilistic responses generated by our improvisational response component.

PDF Details

IJCAI Conference 2011 Conference Paper

SMT Versus AI Redux: How Semantic Frames Evaluate MT More Accurately

Chi-kiu Lo
Dekai Wu

We argue for an alternative paradigm in evaluating machine translation quality that is strongly empirical but more accurately reflects the utility of translations, by returning to a representational foundation based on AI oriented lexical semantics, rather than the superficial flat n-gram and string representations recently dominating the field. Driven by such metrics as BLEU and WER, current SMT frequently produces unusable translations where the semantic event structure is mistranslated: who did what to whom, when, where, why, and how? We argue that it is time for a new generation of more "intelligent" automatic and semi-automatic metrics, based clearly on getting the structure right at the lexical semantics level. We show empirically that it is possible to use simple PropBank style semantic frame representations to surpass all currently widespread metrics' correlation to human adequacy judgments, including even HTER. We also show that replacing human annotators with automatic semantic role labeling still yields much of the advantage of the approach. We combine the best of both worlds: from an SMT perspective, we provide superior yet low-cost quantitative objective functions for translation quality; and yet from an AI perspective, we regain the representational transparency and clear reflection of semantic utility of structural frame-based knowledge representations.

PDF Details DOI

AAAI Conference 1993 Conference Paper

Estimating Probability Distributions over Hypotheses with Variable Unification

Dekai Wu

We analyze the difficulties in applying Bayesian belief networks to language interpretation domains, which typically involve many unification hypotheses that posit variable bindings. As an alternative, we observe that the structure of the underlying hypothesis space permits an approximate encoding of the joint distribution based on marginal rather than conditional probabilities. This suggests an implicit binding approach that circumvents the problems with explicit unification hypotheses, while still allowing hypotheses with alternative unifications to interact probabilistically. The proposed method accepts arbitrary subsets of hypotheses and marginal probability constraints, is robust, and is readily incorporated into standard unification-based and frame-based models.

PDF Details

IJCAI Conference 1989 Conference Paper

A Probabilistic Approach to Marker Propagation

Dekai Wu

Potentially, the advantages of marker-passing over local connectionist techniques for associa tive inference are (1) the ability to differen tiate variable bindings, and (2) reduction in the search space and/or number of processing elements. However, the latter advantage has mostly been realized at the expense of accu racy and predictability. In this paper we con sider a class of associative inference to which marker passing is often applied, variously called abductive inference, schema selection, or pat tern completion. Analysis of marker seman tics in a standard semantic net representation leads to a proposal for more strictly regulated marker propagation. An implementation strat egy employing an augmented relaxation net work is outlined.

PDF