Schema2QA: High-Quality and Low-Cost Q&amp;A Agents for the Structured Web

Xu, Silei; Campagna, G.; Li, Jian; Lam, Monica S.

doi:10.1145/3340531.3411974

Cited by 14 publications

(22 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Empirical results on benchmark datasets demonstrate the superiority of our approach in both language modeling and auto-regressive generation. While the proposed method focuses on the fundamental text modeling, it is also promising to extend to more applications such as machine translation [36]- [40], question answering [41], log generation [42], [43], and code generation [44], [45].…”

Section: Discussionmentioning

confidence: 99%

Discrete Auto-regressive Variational Attention Models for Text Modeling

Fang¹,

Bai²,

Li³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Variational autoencoders (VAEs) have been widely applied for text modeling. In practice, however, they are troubled by two challenges: information underrepresentation and posterior collapse. The former arises as only the last hidden state of LSTM encoder is transformed into the latent space, which is generally insufficient to summarize the data. The latter is a longstanding problem during the training of VAEs as the optimization is trapped to a disastrous local optimum. In this paper, we propose Discrete Auto-regressive Variational Attention Model (DAVAM) to address the challenges. Specifically, we introduce an auto-regressive variational attention approach to enrich the latent space by effectively capturing the semantic dependency from the input. We further design discrete latent space for the variational attention and mathematically show that our model is free from posterior collapse. Extensive experiments on language modeling tasks demonstrate the superiority of DAVAM against several VAE counterparts. Code will be released.

show abstract

Section: Discussionmentioning

confidence: 99%

Discrete Auto-regressive Variational Attention Models for Text Modeling

Fang¹,

Bai²,

Li³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…This paper presents SPL, a toolkit and methodology to extend and localize semantic parsers to a new language with higher accuracy, yet at a fraction of the cost compared to previous methods. SPL was incorporated into the Schema2QA toolkit (Xu et al, 2020a) to give it a multilingual capability.…”

Section: Discussionmentioning

confidence: 99%

“…Only a couple of hundred of sentences need to be translated manually; no manual annotation of sentences is necessary. • An improved neural semantic parsing model, based on BERT-LSTM (Xu et al, 2020a) but using the XLM-R encoder. Its applicability extends beyond multilingual semantic parsing task, as it can be deployed for any NLP task that can be framed as sequence-to-sequence.…”

Section: Cross-attention Weightsmentioning

confidence: 99%

See 1 more Smart Citation

Localizing Open-Ontology QA Semantic Parsers in a Day Using Machine Translation

Moradshahi¹,

Campagna²,

J.³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Self Cite

View full text Add to dashboard Cite

We propose Semantic Parser Localizer (SPL), a toolkit that leverages Neural Machine Translation (NMT) systems to localize a semantic parser for a new language. Our methodology is to (1) generate training data automatically in the target language by augmenting machine-translated datasets with local entities scraped from public websites, (2) add a fewshot boost of human-translated sentences and train a novel XLMR-LSTM semantic parser, and (3) test the model on natural utterances curated using human translators.We assess the effectiveness of our approach by extending the current capabilities of Schema2QA, a system for English Question Answering (QA) on the open web, to 10 new languages for the restaurants and hotels domains. Our models achieve an overall test accuracy ranging between 61% and 69% for the hotels domain and between 64% and 78% for restaurants domain, which compares favorably to 69% and 80% obtained for English parser trained on gold English data and a few examples from validation set. We show our approach outperforms the previous state-of-theart methodology by more than 30% for hotels and 40% for restaurants with localized ontologies for the subset of languages tested.Our methodology enables any software developer to add a new language capability to a QA system for a new domain, leveraging machine translation, in less than 24 hours. Our code is released open-source. 1

show abstract

“…To translate natural language instructions into ThingTalk, we use the previously proposed BERT-LSTM model (Xu et al, 2020). BERT-LSTM is an encoder-decoder network that uses a pretrained BERT encoder (Devlin et al, 2019) and LSTM (Hochreiter and Schmidhuber, 1997) decoder with a pointer-generator (See et al, 2017;Paulus et al, 2018).…”

Section: Semantic Parser Modelmentioning

confidence: 99%

Grounding Open-Domain Instructions to Automate Web Support Tasks

Xu¹,

Masling²,

Du³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

Self Cite

View full text Add to dashboard Cite

Grounding natural language instructions on the web to perform previously unseen tasks enables accessibility and automation. We introduce a task and dataset to train AI agents from open-domain, step-by-step instructions originally written for people. We build RUSS (Rapid Universal Support Service) to tackle this problem. RUSS consists of two models: First, a BERT-LSTM with pointers parses instructions to ThingTalk, a domain-specific language we design for grounding natural language on the web. Then, a grounding model retrieves the unique IDs of any webpage elements requested in ThingTalk. RUSS may interact with the user through a dialogue (e.g. ask for an address) or execute a web operation (e.g. click a button) inside the web runtime. To augment training, we synthesize natural language instructions mapped to ThingTalk. Our dataset consists of 80 different customer service problems from help websites, with a total of 741 step-by-step instructions and their corresponding actions. RUSS achieves 76.7% end-to-end accuracy predicting agent actions from single instructions. It outperforms stateof-the-art models that directly map instructions to actions without ThingTalk. Our user study shows that RUSS is preferred by actual users over web navigation.

show abstract

Schema2QA: High-Quality and Low-Cost Q&A Agents for the Structured Web

Cited by 14 publications

References 17 publications

Discrete Auto-regressive Variational Attention Models for Text Modeling

Discrete Auto-regressive Variational Attention Models for Text Modeling

Localizing Open-Ontology QA Semantic Parsers in a Day Using Machine Translation

Grounding Open-Domain Instructions to Automate Web Support Tasks

Contact Info

Product

Resources

About