Mrinmaya Sachan

Spatial compactness meets topical consistency: jointly modeling links and content for community detection

In this paper, we address the problem of discovering topically meaningful, yet compact (densely connected) communities in a social network. Assuming the social network to be an integer-weighted graph (where the weights can be intuitively defined as the number of common friends, followers, documents exchanged, etc.), we transform the social network to a more efficient representation. In this new representation, each user is a bag of her one-hop neighbors. We propose a mixed-membership model to identify compact communities using this transformation. Next, we augment the representation and the model to incorporate user-content information imposing topical consistency in the communities. In our model a user can belong to multiple communities and a community can participate in multiple topics. This allows us to discover community memberships as well as community and user interests. Our method outperforms other well known baselines on two real-world social networks. Finally, we also provide a fast, parallel approximation of the same.

Science Question Answering using Instructional Materials.

We provide a solution for elementary science test using instructional materials. We posit that there is a hidden structure that explains the correctness of an answer given the question and instructional materials and present a unified max-margin framework that learns to find these hidden structures (given a corpus of question-answer pairs and instructional materials), and uses what it learns to answer novel elementary science questions. Our evaluation shows that our framework outperforms several strong baselines.

Learning Answer-Entailing Structures for Machine Comprehension

Understanding open-domain text is one of the primary challenges in NLP. Machine comprehension evaluates the system’s ability to understand text through a series of question-answering tasks on short pieces of text such that the correct answer can be found only in the given text. For this task, we posit that there is a hidden (latent) structure that explains the relation between the question, correct answer, and text. We call this the answer-entailing structure; given the structure, the correctness of the answer is evident. Since the structure is latent, it must be inferred. We present a unified max-margin framework that learns to find these hidden structures (given a corpus of question-answer pairs), and uses what it learns to answer machine comprehension questions on novel texts. We extend this framework to incorporate multi-task learning on the different subtasks that are required to perform machine comprehension. Evaluation on a publicly available dataset shows that our framework outperforms various IR and neuralnetwork baselines, achieving an overall accuracy of 67.8% (vs. 59.9%, the best previously-published result.)

Learning Concept Taxonomies from Multi-modal Data

We study the problem of automatically building hypernym taxonomies from textual and visual data. Previous works in taxonomy induction generally ignore the increasingly prominent visual data, which encode important perceptual semantics. Instead, we propose a probabilistic model for taxonomy induction by jointly leveraging text and images. To avoid hand-crafted feature engineering, we design end-to-end features based on distributed representations of images and words. The model is discriminatively trained given a small set of existing ontologies and is capable of building full taxonomies from scratch for a collection of unseen conceptual label items with associated images. We evaluate our model and features on the WordNet hierarchies, where our system outperforms previous approaches by a large gap.

Machine Comprehension using Rich Semantic Representations

Machine comprehension tests the system’s ability to understand a piece of text through a reading comprehension task. For this task, we propose an approach using the Abstract Meaning Representation (AMR) formalism. We construct meaning representation graphs for the given text and for each question-answer pair by merging the AMRs of comprising sentences using cross-sentential phenomena such as coreference and rhetorical structures. Then, we reduce machine comprehension to a graph containment problem. We posit that there is a latent mapping of the question-answer meaning representation graph onto the text meaning representation graph that explains the answer. We present a unified max-margin framework that learns to find this mapping (given a corpus of texts and question-answer pairs), and uses what it learns to answer questions on novel texts. We show that this approach leads to state of the art results on the task.

Collective matrix factorization for co-clustering

We outline some matrix factorization approaches for co- clustering polyadic data (like publication data) using non-negative factorization (NMF). NMF approximates the data as a product of non-negative low-rank matrices, and can induce desirable clustering properties in the matrix factors through a flexible range of constraints. We show that simultaneous factorization of one or more matrices provides potent approaches for co-clustering.

Easy Questions First? A Case Study on Curriculum Learning for Question Answering.

Cognitive science researchers have emphasized the importance of ordering a complex task into a sequence of easy to hard problems. Such an ordering provides an easier path to learning and increases the speed of acquisition of the task compared to conventional learning. Recent works in machine learning have explored a curriculum learning approach called selfpaced learning which orders data samples on the easiness scale so that easy samples can be introduced to the learning algorithm first and harder samples can be introduced successively. We introduce a number of heuristics that improve upon selfpaced learning. Then, we argue that incorporating easy, yet, a diverse set of samples can further improve learning. We compare these curriculum learning proposals in the context of four non-convex models for QA and show that they lead to real improvements in each of them.

Parsing to Programs: A Framework for Situated QA

This paper introduces Parsing to Programs, a framework that combines ideas from parsing and probabilistic programming for situated question answering. As a case study, we build a system that solves pre-university level Newtonian physics questions. Our approach represents domain knowledge of Newtonian physics as programs. When presented with a novel question, the system learns a formal representation of the question by combining interpretations from the question text and any associated diagram. Finally, the system uses this formal representation to solve the questions using the domain knowledge. We collect a new dataset of Newtonian physics questions from a number of textbooks and use it to train our system. The system achieves near human performance on held-out textbook questions and section 1 of AP Physics C mechanics - both on practice questions as well as on freely available actual exams held in 1998 and 2012.

Solving electrical networks to incorporate supervision in random walks

Random walks is one of the most popular ideas in computer science. A critical assumption in random walks is that the probability of the walk being at a given vertex at a time instance converges to a limit independent of the start state. While this makes it computationally efficient to solve, it limits their use to incorporate label information. In this paper, we exploit the connection between Random Walks and Electrical Networks to incorporate label information in classification, ranking, and seed expansion.