Search

Language “in the wild” is complex and ambiguous and relies on a shared understanding of the world for its interpretation. Most current natural language processing methods represent language by learning word co-occurrence patterns from massive amounts of linguistic data. This representation can be very powerful, but it is insufficient to capture the meaning behind written and spoken communication. In this dissertation, I will motivate neural-symbolic representations for dealing with these challenges. On the one hand, symbols have inherent explanatory power, and they can help us express contextual knowledge and enforce consistency across different decisions. On the other hand, neural networks allow us to learn expressive distributed representations and make sense of large amounts of linguistic data. I will introduce a holistic framework that covers all stages of the neural-symbolic pipeline: modeling, learning, inference, and its application for diverse discourse scenarios, such as analyzing online discussions, mining argumentative structures, and understanding public discourse at scale. I will show the advantages of neural-symbolic representations with respect to end-to-end neural approaches and traditional statistical relational learning methods. In addition to this, I will demonstrate the advantages of neural-symbolic representations for learning in low-supervision settings, as well as their capabilities to decompose and explain high-level decision. Lastly, I will explore interactive protocols to help human experts in making sense of large repositories of textual data, and leverage neural-symbolic representations as the interface to inject expert human knowledge in the process of partitioning, classifying and organizing large language resources.

Understanding narrative text requires capturing characters' motivations, goals, and mental states. This paper proposes an Entity-based Narrative Graph (ENG) to model the internal-states of characters in a story. We explicitly model entities, their interactions and the context in which they appear, and learn rich representations for them. We experiment with different task-adaptive pre-training objectives, in-domain training, and symbolic inference to capture dependencies between different decisions in the output space. We evaluate our model on two narrative understanding tasks: predicting character mental states, and desire fulfillment, and conduct a qualitative analysis., Accepted at NAACL 2021

Expressive text encoders such as RNNs and Transformer Networks have been at the center of NLP models in recent work. Most of the effort has focused on sentence-level tasks, capturing the dependencies between words in a single sentence, or pairs of sentences. However, certain tasks, such as argumentation mining, require accounting for longer texts and complicated structural dependencies between them. Deep structured prediction is a general framework to combine the complementary strengths of expressive neural encoders and structured inference for highly structured domains. Nevertheless, when the need arises to go beyond sentences, most work relies on combining the output scores of independently trained classifiers. One of the main reasons for this is that constrained inference comes at a high computational cost. In this paper, we explore the use of randomized inference to alleviate this concern and show that we can efficiently leverage deep structured prediction and expressive neural encoders for a set of tasks involving complicated argumentative structures., Accepted to EACL 2021

Background Neural tube defects (NTDs) constitute the most frequent group among congenital malformations and are the main cause of neonatal morbimortality. Folic acid (FA) can reduce the risk of pregnancies affected by NTDs. Objective We aimed to investigate whether mandatory folic acid (FA) fortification of flours is cost-effective as compared to non-mandatory fortification, and to verify whether FA dosage, cost composition, and the quality of economic studies influence the cost-effectiveness of outcomes. Methods We conducted a systematic review. The protocol was registered on PROSPERO (CRD 42018115682). A search was conducted using the electronic databases MEDLINE/PubMed, Web of Science, Embase, Scopus, and EBSCO/CINAHL between January 2019 and October 2020 and updated in February 2021. Eligible studies comprised original economic analyses of mandatory FA fortification of wheat and corn flours (maize flours) compared to strategies of non-mandatory fortification in flours and/or use of FA supplements for NTD prevention. The Drummond verification list was used for quality analysis. Results A total of 7,859 studies were identified, of which 13 were selected. Most (77%; n = 10) studies originated from high-income countries, while three (23%) were from upper-middle-income countries. Results of a cost-effectiveness analysis showed that fortification is cost-effective for NTD prevention, except for in one study in New Zealand. The cost-benefit analysis yielded a median ratio of 17.5:1 (0.98:1 to 417.1:1), meaning that for each monetary unit spent in the program, there would be a return of 17.5 monetary units. Even in the most unfavorable case of mandatory fortification, the investment in the program would virtually payoff at a ratio of 1:0.98. All FA dosages were cost-effective and offered positive health gains, except in one study. The outcomes of two studies showed that FA dosages above 300 μg/100 g have a higher CBA ratio. The studies with the inclusion of “loss of consumer choice” in the analysis may alter the fortification cost-efficacy ratio. Conclusion We expect the findings to be useful for public agencies in different countries in decision-making on the implementation and/or continuity of FA fortification as a public policy in NTD prevention.

This paper describes our proposed solution for SemEval 2017 Task 1: Semantic Textual Similarity (Daniel Cer and Specia, 2017). The task aims at measuring the degree of equivalence between sentences given in English. Performance is evaluated by computing Pearson Correlation scores between the predicted scores and human judgements. Our proposed system consists of two subsystems and one regression model for predicting STS scores. The two subsystems are designed to learn Paraphrase and Event Embeddings that can take the consideration of paraphrasing characteristics and sentence structures into our system. The regression model associates these embeddings to make the final predictions. The experimental result shows that our system acquires 0.8 of Pearson Correlation Scores in this task.