A Mixed Hierarchical Attention Based Encoder-Decoder Approach for
            Standard Table Summarization

Jain, Parag; Laha, Anirban; Sankaranarayanan, Karthik; Nema, Preksha; Khapra, Mitesh M.; Shetty, Shreyas

doi:10.18653/v1/n18-2098

Cited by 24 publications

(13 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Supervised NLG requires large-scale parallel corpora for training, which is a major impediment in scaling to diverse use-cases. For example, in the context of commercial dialog systems alone, there are several scenarios where a system's answer (which may be coming from a database (Jain et al 2018)) needs to be transformed either for its tone (politeness, excitedness, etc. ), or its level of formality (casual, formal, etc.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Controllable Text Formalization

Jain¹,

Mishra²,

Azad³

et al. 2019

AAAI

Self Cite

View full text Add to dashboard Cite

We propose a novel framework for controllable natural language transformation. Realizing that the requirement of parallel corpus is practically unsustainable for controllable generation tasks, an unsupervised training scheme is introduced. The crux of the framework is a deep neural encoder-decoder that is reinforced with text-transformation knowledge through auxiliary modules (called scorers). These scorers, based on off-the-shelf language processing tools, decide the learning scheme of the encoder-decoder based on its actions. We apply this framework for the text-transformation task of formalizing an input text by improving its readability grade; the degree of required formalization can be controlled by the user at run-time. Experiments on public datasets demonstrate the efficacy of our model towards: (a) transforming a given text to a more formal style, and (b) varying the amount of formalness in the output text based on the specified input control. Our code and datasets are released for academic use.

show abstract

Section: Introductionmentioning

confidence: 99%

Unsupervised Controllable Text Formalization

Jain¹,

Mishra²,

Azad³

et al. 2019

AAAI

Self Cite

View full text Add to dashboard Cite

show abstract

“…Such systems include the ones by Lebret, Grangier, and Auli (2016), who use conditional language model with copy mechanism for generation, Liu et al (2017), who propose a dual attention Seq2Seq model, Nema et al (2018), who use gated orthogonalization along with dual attention, and Bao et al (2018), who introduce a flexible copying mechanism that selectively replicates contents from the table in the output sequence. Other systems revolve around popular data sets such as the WEATHERGOV data set (Liang, Jordan, and Klein 2009;Jain et al 2018), ROBOCUP data set (Chen and Mooney 2008), ROTOWIRE and SBNATION (Wiseman, Shieber, and Rush 2017), and the WEBNLG data set (Gardent et al 2017). Recently Bao et al (2018) andNovikova, Dusek, andRieser (2017) have introduced a new data set for table/tuple to text generation, and both supervised and unsupervised systems (Fevry and Phang 2018) have been proposed and evaluated against these data sets.…”

Section: Related Workmentioning

confidence: 99%

Scalable Micro-planned Generation of Discourse from Structured Data

Laha

Jain

Mishra³

et al. 2020

Computational Linguistics

Self Cite

View full text Add to dashboard Cite

We present a framework for generating natural language description from structured data such as tables; the problem comes under the category of data-to-text natural language generation (NLG). Modern data-to-text NLG systems typically employ end-to-end statistical and neural architectures that learn from a limited amount of task-specific labeled data, and therefore, exhibit limited scalability, domain-adaptability, and interpretability. Unlike these systems, ours is a modular, pipeline-based approach, and does not require task-specific parallel data. It rather relies on monolingual corpora and basic off-the-shelf NLP tools. This makes our system more scalable and easily adaptable to newer domains.Our system employs a 3-staged pipeline that: (i) converts entries in the structured data to canonical form, (ii) generates simple sentences for each atomic entry in the canonicalized representation, and (iii) combines the sentences to produce a coherent, fluent and adequate paragraph description through sentence compounding and co-reference replacement modules. Experiments on a benchmark mixed-domain dataset curated for paragraph description from tables reveals the superiority of our system over existing data-to-text approaches. We also demonstrate the robustness of our system in accepting other popular datasets covering diverse data types such as Knowledge Graphs and Key-Value maps. * The first three authors have equally contributed to the work Submission

show abstract

“…Trisedya et al (2018) propose a GTR-LSTM model to encode not only the triple information, but also the structure information of the entity graph into hidden semantic space. Jain et al (2018) exploit a mixed hierarchical attention based encoder-decoder model to leverage the structure and content information. Shimorina and Gardent (2018) propose to use delexicalization and copy mechanism to enhance the performance of the sequence-to-sequence framework.…”

Section: Related Workmentioning

confidence: 99%

Dynamic Topic Tracker for KB-to-Text Generation

Lam

Jameel

2020

Proceedings of the 28th International Conference on Computational Linguistics

View full text Add to dashboard Cite

Recently, many KB-to-text generation tasks have been proposed to bridge the gap between knowledge bases and natural language by directly converting a group of knowledge base triples into human-readable sentences. However, most of the existing models suffer from the off-topic problem, namely, the models are prone to generate some unrelated clauses that are somehow involved with certain input terms regardless of the given input data. This problem seriously degrades the quality of the generation results. In this paper, we propose a novel dynamic topic tracker for solving this problem. Different from existing models, our proposed model learns a global hidden representation for topics and recognizes the corresponding topic during each generation step. The recognized topic is used as additional information to guide the generation process and thus alleviates the off-topic problem. The experimental results show that our proposed model can enhance the performance of sentence generation and the off-topic problem is significantly mitigated.

show abstract

A Mixed Hierarchical Attention Based Encoder-Decoder Approach for Standard Table Summarization

Cited by 24 publications

References 10 publications

Unsupervised Controllable Text Formalization

Unsupervised Controllable Text Formalization

Scalable Micro-planned Generation of Discourse from Structured Data

Dynamic Topic Tracker for KB-to-Text Generation

Contact Info

Product

Resources

About