The old Asian legend about the blind men and the elephant comes to mind when looking at how different authors of scientific papers describe a piece of related prior work. It turns out that different citations to the same paper often focus on different aspects of that paper and that neither provides a full description of its full set of contributions. In this article, we will describe our investigation of this phenomenon. We studied citation summaries in the context of research papers in the biomedical domain. A citation summary is the set of citing sentences for a given article and can be used as a surrogate for the actual article in a variety of scenarios. It contains information that was deemed by peers to be important. Our study shows that citation summaries overlap to some extent with the abstracts of the papers and that they also differ from them in that they focus on different aspects of these papers than do the abstracts. In addition to this, co-cited articles (which are pairs of articles cited by another article) tend to be similar. We show results based on a lexical similarity metric called cohesion to justify our claims.

Multiple sequence alignment techniques have recently gained popularity in the Natural Language community, especially for tasks such as machine translation, text generation, and paraphrase identification. Prior work falls into two categories, depending on the type of input used: (a) parallel corpora (e.g., multiple translations of the same text) or (b) comparable texts (non-parallel but on the same topic). So far, only techniques based on parallel texts have successfully used syntactic information to guide alignments. In this paper, we describe an algorithm for incorporating syntactic features in the alignment process for non-parallel texts with the goal of generating novel paraphrases of existing texts. Our method uses dynamic programming with alignment decision based on the local syntactic similarity between two sentences. Our results show that syntactic alignment outrivals syntax-free methods by 20% in both grammaticality and fidelity when computed over the novel sentences generated by alignment-induced finite state automata.

Multimodal conversation systems allow users to interact with computers effectively using multiple modalities, such as natural language and gesture. However, these systems have not been widely used in practical applications mainly due to their limited input understanding capability. As a result, conversation systems often fail to understand user requests and leave users frustrated. To address this issue, most existing approaches focus on improving a system's interpretation capability. Nonetheless, such improvements may still be limited, since they would never cover the entire range of input expressions. Alternatively, we present a two-way adaptation framework that allows both users and systems to dynamically adapt to each other's capability and needs during the course of interaction. Compared to existing methods, our approach offers two unique contributions. First, it improves the usability and robustness of a conversation system by helping users to dynamically learn the system's capabilities in context. Second, our approach enhances the overall interpretation capability of a conversation system by learning new user expressions on the fly. Our preliminary evaluation shows the promise of this approach.

No abstract

This interactive presentation describes LexNet, a graphical environment for graph-based NLP developed at the University of Michigan. LexNet includes LexRank (for text summarization), biased LexRank (for passage retrieval), and TUMBL (for binary classification). All tools in the collection are based on random walks on lexical graphs, that is graphs where different NLP objects (e.g., sentences or phrases) are represented as nodes linked by edges proportional to the lexical similarity between the two nodes. We will demonstrate these tools on a variety of NLP tasks including summarization, question answering, and prepositional phrase attachment.