Entity-balanced Gaussian pLSA for Automated Comparison

Contractor, Danish; Singla, Parag

doi:10.18653/v1/n16-1009

Cited by 5 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Probabilistic embeddings have been applied in tasks for building better word representations [3,34], entity comparison [10], facial recognition [7], pose estimation [44], generating multimodal embeddings [2,9], etc. The motivation in some of these tasks is similar to ours -for instance, Qian et al [34] use Gaussian embeddings to represent words to better capture meaning and ambiguity.…”

Section: Probabilistic Embeddingsmentioning

confidence: 99%

Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddings

Pandey¹,

Contractor²,

Joshi³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Embedding-based approaches for dialog response retrieval embed the context-response pairs as points in the embedding space. These approaches are scalable, but fail to account for the complex, manto-many relationships that exist between context-response pairs. On the other end of the spectrum, there are approaches that feed the context-response pairs jointly through multiple layers of neural networks. These approaches can model the complex relationships between context-response pairs, but fail to scale when the set of responses is moderately large (>100). In this paper, we combine the best of both worlds by proposing a scalable model that can learn complex relationships between context-response pairs. Specifically, the model maps the contexts as well as responses to probability distributions over the embedding space. We train the models by optimizing the Kullback-Leibler divergence between the distributions induced by context-response pairs in the training data. We show that the resultant model achieves better performance as compared to other embedding-based approaches on publicly available conversation data.

show abstract

Section: Probabilistic Embeddingsmentioning

confidence: 99%

Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddings

Pandey¹,

Contractor²,

Joshi³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…(b) Hand-designed entity.type and entity.attr specific features. These include indicators for guessing potential types, based on targets of WH ( what , where , which ) words and certain verb classes; multi-sentence features that are based on dependency parses of individual sentences that aid in attribute detection—for example, for every noun and adjective, an attribute indicator feature is on if any of its ancestors is a potential type as indicated by the type feature; indicator features for descriptive phrases (Contractor et al 2016), such as adjective–noun pairs. (c) For each token, we include cluster ids generated from a clustering of word2vec vectors (Mikolov et al 2013) run over a large tourism corpus.…”

Section: Mseq Semantic Labelingmentioning

confidence: 99%

Constrained BERT BiLSTM CRF for understanding multi-sentence entity-seeking questions

Contractor¹,

Patra

Singla

2020

Nat. Lang. Eng.

Self Cite

View full text Add to dashboard Cite

We present the novel task of understanding multi-sentence entity-seeking questions (MSEQs), that is, the questions that may be expressed in multiple sentences, and that expect one or more entities as an answer. We formulate the problem of understanding MSEQs as a semantic labeling task over an open representation that makes minimal assumptions about schema or ontology-specific semantic vocabulary. At the core of our model, we use a BiLSTM (bidirectional LSTM) conditional random field (CRF), and to overcome the challenges of operating with low training data, we supplement it by using BERT embeddings, hand-designed features, as well as hard and soft constraints spanning multiple sentences. We find that this results in a 12–15 points gain over a vanilla BiLSTM CRF. We demonstrate the strengths of our work using the novel task of answering real-world entity-seeking questions from the tourism domain. The use of our labels helps answer 36% more questions with 35% more (relative) accuracy as compared to baselines. We also demonstrate how our framework can rapidly enable the parsing of MSEQs in an entirely new domain with small amounts of training data and little change in the semantic representation.

show abstract

“…(a) Lexical features for capitalization, indicating numerals etc., token-level features based on POS and NER (b) hand-designed x.type and x.attribute specific features. These include indicators for guessing potential types, based on targets of WH (what, where, which) words and certain verb classes; dependency parse features that aid in attribute detection, e.g., for every noun and adjective, an attribute indicator feature is on if any of its ancestors is a potential type as indicated by type feature; indicator features for descriptive phrases (Contractor et al, 2016), such as adjective-noun pairs. (c) For each token, we include cluster ids generated from a clustering of word2vec vectors (Mikolov et al, 2013) run over a large tourism corpus.…”

Section: Supervised Labelingmentioning

confidence: 99%

Towards Understanding and Answering Multi-Sentence Recommendation Questions on Tourism

Contractor,

Patra,

Singla

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

We introduce the first system towards the novel task of answering complex multisentence recommendation questions in the tourism domain. Our solution uses a pipeline of two modules: question understanding and answering. For question understanding, we define an SQL-like query language that captures the semantic intent of a question; it supports operators like subset, negation, preference and similarity, which are often found in recommendation questions. We train and compare traditional CRFs as well as bidirectional LSTM-based models for converting a question to its semantic representation. We extend these models to a semisupervised setting with partially labeled sequences gathered through crowdsourcing. We find that our best model performs semi-supervised training of BiDiL-STM+CRF with hand-designed features and CCM (Chang et al., 2007) constraints.Finally, in an end to end QA system, our answering component converts our question representation into queries fired on underlying knowledge sources. Our experiments on two different answer corpora demonstrate that our system can significantly outperform baselines with up to 20 pt higher accuracy and 17 pt higher recall. *This work was carried out as part of PhD research at IIT Delhi. The author is also a regular employee at IBM Research.

show abstract

Entity-balanced Gaussian pLSA for Automated Comparison

Cited by 5 publications

References 20 publications

Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddings

Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddings

Constrained BERT BiLSTM CRF for understanding multi-sentence entity-seeking questions

Towards Understanding and Answering Multi-Sentence Recommendation Questions on Tourism

Contact Info

Product

Resources

About