Zero-Shot Learning for Semantic Utterance Classification

We propose a novel zero-shot learning method for semantic utterance classification (SUC). It learns a classifier $f: X \to Y$ for problems where none of the semantic categories $Y$ are present in the training set. The framework uncovers the link between categories and utterances using a semantic space. We show that this semantic space can be learned by deep neural networks trained on large amounts of search engine query log data. More precisely, we propose a novel method that can learn discriminative semantic features without supervision. It uses the zero-shot learning framework to guide the learning of the semantic features. We demonstrate the effectiveness of the zero-shot semantic learning algorithm on the SUC dataset collected by (Tur, 2012). Furthermore, we achieve state-of-the-art results by combining the semantic features with a supervised method.

Morphological Disambiguation by Voting Constraints

We present a constraint-based morphological disambiguation system in which individual constraints vote on matching morphological parses, and disambiguation of all the tokens in a sentence is performed at the end by selecting parses that receive the highest votes. This constraint application paradigm makes the outcome of the disambiguation independent of the rule sequence, and hence relieves the rule developer from worrying about potentially conflicting rule sequencing. Our results for disambiguating Turkish indicate that using about 500 constraint rules and some additional simple statistics, we can attain a recall of 95-96% and a precision of 94-95% with about 1.01 parses per token. Our system is implemented in Prolog and we are currently investigating an efficient implementation based on finite state transducers.

Using Multiple Sources of Information for Constraint-Based Morphological Disambiguation

This thesis presents a constraint-based morphological disambiguation approach that is applicable to languages with complex morphology--specifically agglutinative languages with productive inflectional and derivational morphological phenomena. For morphologically complex languages like Turkish, automatic morphological disambiguation involves selecting for each token morphological parse(s), with the right set of inflectional and derivational markers. Our system combines corpus independent hand-crafted constraint rules, constraint rules that are learned via unsupervised learning from a training corpus, and additional statistical information obtained from the corpus to be morphologically disambiguated. The hand-crafted rules are linguistically motivated and tuned to improve precision without sacrificing recall. In certain respects, our approach has been motivated by Brill's recent work, but with the observation that his transformational approach is not directly applicable to languages like Turkish. Our approach also uses a novel approach to unknown word processing by employing a secondary morphological processor which recovers any relevant inflectional and derivational information from a lexical item whose root is unknown. With this approach, well below 1% of the tokens remains as unknown in the texts we have experimented with. Our results indicate that by combining these hand-crafted, statistical and learned information sources, we can attain a recall of 96 to 97% with a corresponding precision of 93 to 94%, and ambiguity of 1.02 to 1.03 parses per token.

Combining Hand-crafted Rules and Unsupervised Learning in Constraint-based Morphological Disambiguation

This paper presents a constraint-based morphological disambiguation approach that is applicable languages with complex morphology--specifically agglutinative languages with productive inflectional and derivational morphological phenomena. In certain respects, our approach has been motivated by Brill's recent work, but with the observation that his transformational approach is not directly applicable to languages like Turkish. Our system combines corpus independent hand-crafted constraint rules, constraint rules that are learned via unsupervised learning from a training corpus, and additional statistical information from the corpus to be morphologically disambiguated. The hand-crafted rules are linguistically motivated and tuned to improve precision without sacrificing recall. The unsupervised learning process produces two sets of rules: (i) choose rules which choose morphological parses of a lexical item satisfying constraint effectively discarding other parses, and (ii) delete rules, which delete parses satisfying a constraint. Our approach also uses a novel approach to unknown word processing by employing a secondary morphological processor which recovers any relevant inflectional and derivational information from a lexical item whose root is unknown. With this approach, well below 1 percent of the tokens remains as unknown in the texts we have experimented with. Our results indicate that by combining these hand-crafted,statistical and learned information sources, we can attain a recall of 96 to 97 percent with a corresponding precision of 93 to 94 percent, and ambiguity of 1.02 to 1.03 parses per token.