Madeeswaran Kannan


2021

pdf bib
Exploring Input Representation Granularity for Generating Questions Satisfying Question-Answer Congruence
Madeeswaran Kannan | Haemanth Santhi Ponnusamy | Kordula De Kuthy | Lukas Stein | Detmar Meurers
Proceedings of the 14th International Conference on Natural Language Generation

In question generation, the question produced has to be well-formed and meaningfully related to the answer serving as input. Neural generation methods have predominantly leveraged the distributional semantics of words as representations of meaning and generated questions one word at a time. In this paper, we explore the viability of form-based and more fine-grained encodings, such as character or subword representations for question generation. We start from the typical seq2seq architecture using word embeddings presented by De Kuthy et al. (2020), who generate questions from text so that the answer given in the input text matches not just in meaning but also in form, satisfying question-answer congruence. We show that models trained on character and subword representations substantially outperform the published results based on word embeddings, and they do so with fewer parameters. Our approach eliminates two important problems of the word-based approach: the encoding of rare or out-of-vocabulary words and the incorrect replacement of words with semantically-related ones. The character-based model substantially improves on the published results, both in terms of BLEU scores and regarding the quality of the generated question. Going beyond the specific task, this result adds to the evidence weighing different form- and meaning-based representations for natural language processing tasks.

pdf bib
Advancing Neural Question Generation for Formal Pragmatics: Learning when to generate and when to copy
Kordula De Kuthy | Madeeswaran Kannan | Haemanth Santhi Ponnusamy | Detmar Meurers
Proceedings of the First Workshop on Integrating Perspectives on Discourse Annotation

2020

pdf bib
TüKaPo at SemEval-2020 Task 6: Def(n)tly Not BERT: Definition Extraction Using pre-BERT Methods in a post-BERT World
Madeeswaran Kannan | Haemanth Santhi Ponnusamy
Proceedings of the Fourteenth Workshop on Semantic Evaluation

We describe our system (TüKaPo) submitted for Task 6: DeftEval, at SemEval 2020. We developed a hybrid approach that combined existing CNN and RNN methods and investigated the impact of purely-syntactic and semantic features on the task of definition extraction. Our final model achieved a F1-score of 0.6851 in subtask 1, i.e, sentence classification.

pdf bib
Towards automatically generating Questions under Discussion to link information and discourse structure
Kordula De Kuthy | Madeeswaran Kannan | Haemanth Santhi Ponnusamy | Detmar Meurers
Proceedings of the 28th International Conference on Computational Linguistics

Questions under Discussion (QUD; Roberts, 2012) are emerging as a conceptually fruitful approach to spelling out the connection between the information structure of a sentence and the nature of the discourse in which the sentence can function. To make this approach useful for analyzing authentic data, Riester, Brunetti & De Kuthy (2018) presented a discourse annotation framework based on explicit pragmatic principles for determining a QUD for every assertion in a text. De Kuthy et al. (2018) demonstrate that this supports more reliable discourse structure annotation, and Ziai and Meurers (2018) show that based on explicit questions, automatic focus annotation becomes feasible. But both approaches are based on manually specified questions. In this paper, we present an automatic question generation approach to partially automate QUD annotation by generating all potentially relevant questions for a given sentence. While transformation rules can concisely capture the typical question formation process, a rule-based approach is not sufficiently robust for authentic data. We therefore employ the transformation rules to generate a large set of sentence-question-answer triples and train a neural question generation model on them to obtain both systematic question type coverage and robustness.

2019

pdf bib
TüKaSt at SemEval-2019 Task 6: Something Old, Something Neu(ral): Traditional and Neural Approaches to Offensive Text Classification
Madeeswaran Kannan | Lukas Stein
Proceedings of the 13th International Workshop on Semantic Evaluation

We describe our system (TüKaSt) submitted for Task 6: Offensive Language Classification, at SemEval 2019. We developed multiple SVM classifier models that used sentence-level dense vector representations of tweets enriched with sentiment information and term-weighting. Our best results achieved F1 scores of 0.734, 0.660 and 0.465 in the first, second and third sub-tasks respectively. We also describe a neural network model that was developed in parallel but not used during evaluation due to time constraints.

2016

pdf bib
Online Information Retrieval for Language Learning
Maria Chinkina | Madeeswaran Kannan | Detmar Meurers
Proceedings of ACL-2016 System Demonstrations