One of the key concerns in computational semantics is to construct a domain independent semantic representation which captures the richness of natural language, yet can be quickly customized to a specific domain for practical applications. We propose to use generic semantic frames defined in FrameNet, a domain-independent semantic resource, as an intermediate semantic representation for language understanding in dialog systems. In this paper we: (a) outline a novel method for FrameNet-style semantic dependency labeling that builds on a syntactic dependency parse; and (b) compare the accuracy of domain-adapted and generic approaches to semantic parsing for dialog tasks, using a frame-annotated corpus of human-computer dialogs in an airline reservation domain.

Cross-lingual model transfer has been a promising approach for inducing dependency parsers for low-resource languages where annotated treebanks are not available. The major obstacles for the model transfer approach are two-fold: 1. Lexical features are not directly transferable across languages; 2. Target language-specific syntactic structures are difficult to be recovered. To address these two challenges, we present a novel representation learning framework for multi-source transfer parsing. Our framework allows multi-source transfer parsing using full lexical features straightforwardly. By evaluating on the Google universal dependency treebanks (v2.0), our best models yield an absolute improvement of 6.53% in averaged labeled attachment score, as compared with delexicalized multi-source transfer models. We also significantly outperform the state-of-the-art transfer system proposed most recently.

We advance the state of the art in biomolecular interaction extraction with three contributions: (i) We show that deep, Abstract Meaning Representations (AMR) significantly improve the accuracy of a biomolecular interaction extraction system when compared to a baseline that relies solely on surface- and syntax-based features; (ii) In contrast with previous approaches that infer relations on a sentence-by-sentence basis, we expand our framework to enable consistent predictions over sets of sentences (documents); (iii) We further modify and expand a graph kernel learning framework to enable concurrent exploitation of automatically induced AMR (semantic) and dependency structure (syntactic) representations. Our experiments show that our approach yields interaction extraction systems that are more robust in environments where there is a significant mismatch between training and test conditions.

Studying characters plays a vital role in computationally representing and interpreting narratives. Unlike previous work, which has focused on inferring character roles, we focus on the problem of modeling their relationships. Rather than assuming a fixed relationship for a character pair, we hypothesize that relationships temporally evolve with the progress of the narrative, and formulate the problem of relationship modeling as a structured prediction problem. We propose a semi-supervised framework to learn relationship sequences from fully as well as partially labeled data. We present a Markovian model capable of accumulating historical beliefs about the relationship and status changes. We use a set of rich linguistic and semantically motivated features that incorporate world knowledge to investigate the textual content of narrative. We empirically demonstrate that such a framework outperforms competitive baselines.

Unlike traditional machine learning methods, humans often learn from natural language instruction. As users become increasingly accustomed to interacting with mobile devices using speech, their interest in instructing these devices in natural language is likely to grow. We introduce our Learning by Instruction Agent (LIA), an intelligent personal agent that users can teach to perform new action sequences to achieve new commands, using solely natural language interaction. LIA uses a CCG semantic parser to ground the semantics of each command in terms of primitive executable procedures defining sensors and effectors of the agent. Given a natural language command that LIA does not understand, it prompts the user to explain how to achieve the command through a sequence of steps, also specified in natural language. A novel lexicon induction algorithm enables LIA to generalize across taught commands, e.g., having been taught how to "forward an email to Alice," LIA can correctly interpret the command "forward this email to Bob." A user study involving email tasks demonstrates that users voluntarily teach LIA new commands, and that these taught commands significantly reduce task completion time. These results demonstrate the potential of natural language instruction as a significant, under-explored paradigm for machine learning.

We present a novel annotation framework for representing predicate-argument structures, which uses dependency trees to encode the syntactic and semantic roles of a sentence simultaneously. The main contribution is a semantic role transmission model, which eliminates the structural gap between syntax and shallow semantics, making them compatible. A Chinese semantic treebank was built under the proposed framework, and the first release containing about 14K sentences is made freely available. The proposed framework enables semantic role labeling to be solved as a sequence labeling task, and experiments show that standard sequence labelers can give competitive performance on the new treebank compared with state-of-the-art graph structure models.

We present the first probabilistic model to capture all levels of the Minsky Frame structure, with the goal of corpus-based induction of scenario definitions. Our model unifies prior efforts in discourse-level modeling with that of Fillmore's related notion of frame, as captured in sentence-level, FrameNet semantic parses; as part of this, we resurrect the coupling among Minsky's frames, Schank's scripts and Fillmore's frames, as originally laid out by those authors. Empirically, our approach yields improved scenario representations, reflected quantitatively in lower surprisal and more coherent latent scenarios.

Robust intelligent systems may leverage knowledge about the world to cope with a variety of contexts.While automatic knowledge extraction algorithms have been successfully used to build knowledge bases in English,little progress has been made in extracting non-alphabetic languages, e.g. Chinese.This paper identifies the key challenge in instance and pattern extraction for Chinese and presents the Coupled Chinese Pattern Learner that utilizes part-of-speech tagging and language-dependent grammar rules for generalized matching in the Chinese never-ending language learner framework for large-scale knowledge extraction from online documents.Experiments showed that the proposed system is scalable and achieves a precision of 79.9% in learning categories after a small number of iterations.

To enable effective collaborations between humans and cognitive robots, it is important for robots to continuously acquire task knowledge from human partners. To address this issue, we are currently developing a framework that supports task learning through visual demonstration and natural language dialogue. One core component of this framework is the integration of language and vision that is driven by dialogue for task knowledge learning. This paper describes our on-going effort, particularly, grounded task learning through joint processing of video and dialogue using And-Or-Graphs (AOG).

This paper describes R3 (Reading, Reasoning, and Reporting), our system for deep language understanding and model management for the biomedical domain. Starting from a base BioPAX model, we learn extensions to it by reading biomedical research articles from PubMed Central. We describe the particular issues for text understanding in this domain and how we use pre- and post-analysis reasoning to bridge the differences in how knowledge is packaged in a text and in a biomedical database. We close with brief description of our first year results, where R3 was faster than all other reported systems, reading 1,000 articles in 15 minutes.