Articles

Neural Machine Translation (NMT) based on the encoder-decoder architecture has recently become a new paradigm. Researchers have proven that the target-side monolingual data can greatly enhance the decoder model of NMT. However, the source-side monolingual data is not fully explored although it should be useful to strengthen the encoder model …...

We investigate whether a neural, encoder- decoder translation system learns syntactic in- formation on the source side as a by-product of training. We propose two methods to de- tect whether the encoder has learned local and global source syntax. A fine-grained analy- sis of the syntactic structure learned by the …...

We present CHARAGRAM embeddings, a sim- ple approach for learning character-based compositional models to embed textual se- quences. A word or sentence is represented using a character n-gram count vector, fol- lowed by a single nonlinear transformation to yield a low-dimensional embedding. We use three tasks for evaluation: word simi- …...

Encoder-decoder networks are popular for modeling sequences probabilistically in many applications. These models use the power of the Long Short-Term Memory (LSTM) archi- tecture to capture the full dependence among variables, unlike earlier models like CRFs that typically assumed conditional independence among non-adjacent variables. However in practice encoder-decoder models exhibit …...

We present an approach to simultaneously per- form semantic segmentation and prepositional phrase attachment resolution for captioned images. Some ambiguities in language can- not be resolved without simultaneously rea- soning about an associated image. If we con- sider the sentence “I shot an elephant in my pajamas”, looking at language …...

To enable language-based communication and collaboration with cognitive robots, this paper presents an approach where an agent can learn task models jointly from language instruction and visual demonstration using an And-Or Graph (AoG) representation. The learned AoG captures a hierarchical task structure where linguistic labels (for language communication) are grounded …...

Entity linking is the task of identifying men- tions of entities in text, and linking them to entries in a knowledge base. This task is espe- cially difficult in microblogs, as there is little additional text to provide disambiguating con- text; rather, authors rely on an implicit com- mon ground …...

Named Entity Recognition is a well estab- lished information extraction task with many state of the art systems existing for a va- riety of languages. Most systems rely on language specific resources, large annotated corpora, gazetteers and feature engineering to perform well monolingually. In this pa- per, we introduce an …...

For AI systems to reason about real world situ- ations, they need to recognize which processes are at play and which entities play key roles in them. Our goal is to extract this kind of role- based knowledge about processes, from mul- tiple sentence-level descriptions. This knowl- edge is hard …...

When interacting individuals entrain, they be- gin to speak more like each other. To sup- port research on entrainment in cooperative multi-party dialogues, we have created a cor- pus where teams of three or four speakers play two rounds of a cooperative board game. We describe the experimental design and …...

In this paper, we present a study on per- sonalized emphasis framing which can be used to tailor the content of a message to enhance its appeal to different individ- uals. With this framework, we directly model content selection decisions based on a set of psychologically-motivated domain- independent personal traits …...

We present an unsupervised model for the discovery and clustering of latent “personas” (characterizations of entities). Our model simultaneously clusters documents featuring similar collections of personas. We evalu- ate this model on a collection of news arti- cles about immigration, showing that personas help predict the coarse-grained framing anno- tations …...

The goal of language modeling techniques is to capture the statistical and structural prop- erties of natural languages from training cor- pora. This task typically involves the learning of short range dependencies, which generally model the syntactic properties of a language and/or long range dependencies, which are se- mantic in …...

Methods based on representation learning cur- rently hold the state-of-the-art in many natural language processing and knowledge base in- ference tasks. Yet, a major challenge is how to efficiently incorporate commonsense knowl- edge into such models. A recent approach reg- ularizes relation and entity representations by propositionalization of first-order logic …...

In this paper, we improve microblog users’ demographic prediction by fully utilizing their video related behaviors. First, we collect the describing words of currently popular videos, including video names, actor names and video keywords, from video websites. Secondly, we search these describing words in users’ microblogs, and build the direct …...

Distant supervision has been widely used in current systems of fine-grained entity typ- ing to automatically assign categories (en- tity types) to entity mentions. However, the types so obtained from knowledge bases are often incorrect for the entity mention’s local context. This paper proposes a novel em- bedding method to …...

Research accomplishment is usually measured by considering all citations with equal impor- tance, thus ignoring the wide variety of pur- poses an article is being cited for. Here, we posit that measuring the intensity of a refer- ence is crucial not only to perceive better un- derstanding of research endeavor, …...

The Xenotext Experiment implants poetry into an extremophile’s DNA, and uses that DNA to generate new poetry in a protein form. The molecular machinery of life requires that these two poems encipher each other un- der a symmetric substitution cipher. We search for ciphers which permit writing under the Xenotext …...

Directly reading documents and being able to answer questions from them is an unsolved challenge. To avoid its inherent difficulty, ques- tion answering (QA) has been directed towards using Knowledge Bases (KBs) instead, which has proven effective. Unfortunately KBs often suffer from being too restrictive, as the schema cannot support …...

Neural encoder-decoder models have shown great success in many sequence generation tasks. However, previous work has not in- vestigated situations in which we would like to control the length of encoder-decoder out- puts. This capability is crucial for applica- tions such as text summarization, in which we have to generate …...