=Paper=
{{Paper
|id=Vol-2180/paper-37
|storemode=property
|title=Seq2RDF: An End-to-end Application for Deriving Triples from Natural Language Text
|pdfUrl=https://ceur-ws.org/Vol-2180/paper-37.pdf
|volume=Vol-2180
|authors=Yue Liu,Tongtao Zhang,Zhicheng Liang,Heng Ji,Deborah McGuinness
|dblpUrl=https://dblp.org/rec/conf/semweb/LiuZLJM18
}}
==Seq2RDF: An End-to-end Application for Deriving Triples from Natural Language Text==
<pdf width="1500px">https://ceur-ws.org/Vol-2180/paper-37.pdf</pdf>
<pre>
       Seq2RDF: An end-to-end application for
     deriving Triples from Natural Language Text

    Yue Liu, Tongtao Zhang, Zhicheng Liang, Heng Ji, Deborah L. McGuinness

          Department of Computer Science, Rensselaer Polytechnic Institute

        Abstract. We present an end-to-end approach that takes unstructured
        textual input and generates structured output compliant with a given
        vocabulary. We treat the triples within a given knowledge graph as an
        independent graph language and propose an encoder-decoder framework
        with an attention mechanism that leverages knowledge graph embed-
        dings. Our model learns the mapping from natural language text to triple
        representation in the form of subject-predicate-object using the se-
        lected knowledge graph vocabulary. Experiments on three different data
        sets show that we achieve competitive F1-Measures over the baselines
        using our simple yet effective approach. A demo video is included.


1     Introduction
Converting free text into usable structured knowledge for downstream applica-
tions usually requires expert human curators, or relies on the ability of machines
to accurately parse natural language based on the meanings in the knowledge
graph (KG) vocabulary. Despite many advances in text extraction and seman-
tic technologies, there is yet to be a simple system that generates RDF triples
from free text given a chosen KG vocabulary in just one step, which we consider
an end-to-end system. We aim to automate the process of translating a natural
language sentence into a structured triple representation defined in the form of
subject-predicate-object, s-p-o for short, and build an end-to-end model
based on an encoder-decoder architecture that learns the semantic parsing pro-
cess from text to triple without tedious feature engineering and intermediate
steps. We evaluate our approach on three different datasets and achieve com-
petitive F1-measures outperforming our proposed baselines, respectively. The
system, data set and demo are publicly available12 .

2     Our Approach
Inspired by the sequence-to-sequence model[5] in recent Neural Machine Trans-
lation, we attempt to use this model to bridge the gap between natural lan-
guage and triple representation. We consider a natural language sentence X =
[x1 , . . . , x|X| ] as a source sequence, and we aim to map X to an RDF triple
Y = [y1 , y2 , y3 ] with regard to s-p-o as a target sequence that is aligned with
1
    https://github.com/YueLiu/NeuralTripleTranslation
2
    https://youtu.be/ssiQEDF-HHE
a given KG vocabulary set or schema. Given DBpedia for example, we take a
large amount of existing triples from DBpedia as ground truth facts for training.
Our model learns how to form a compliant triple with appropriate terms in the
existing vocabulary. Furthermore, the architecture of the decoder enables the
model to capture the differences, dependencies and constraints when selecting
s-p-o respectively, which makes the model a natural fit for this learning task.

      Lake    George          is          at      the    southeast            base   of   the   Adirondack Mountains



                                                        Bi-directional LSTM



                                                           Concatenate




     Encoder




               <Start_of_Triple>




             dbr:Lake_George_(New_York)                       dbo:country                       dbr:Adirondacks

                  dbr:George_Lake                            dbo:birthplace                 dbr:Adirondack_Mountains
                                                             dbo:location
              dbr:Lake_George_(Florida)                                                     yago:Mountain109359803
                                                              dbo:isPartOf
         dbr:Lake_George_(New_South_Wales)                                                  dbr:Whiteface_Mountain

     Decoder


Fig. 1: Model Overview. Three colors (red, yellow, blue) represent the active attention
during s-p-o decoding respectively. We currently only generate a single triple per
sentence, leaving the generation of multiple triples per sentence for future work.

As shown in Figure 1, the model consists of an encoder taking in a natural
language sentence as sequence input and a decoder generating the target RDF
triple. The model pursues the maximized conditional probability
                                                              3
                                                              Y
                                               p(Y |X) =              p(y|y<td , X),                                   (1)
                                                             td =1

Both encoder and decoder are recurrent neural networks3 with Long Short Term
Memory (LSTM) cells. We apply the attention mechanism that forces the model
to learn to focus on specific parts of the input sequence when decoding, instead
3
    We use tf.contrib.seq2seq.sequence loss which is a weighted cross-entropy loss
    for a sequence of logits. We concatenate the last hidden output of forward and
    backward LSTM networks, the concatenated vector comes with fixed dimensions
of relying only on the last hidden state of the encoder. Furthermore, in order
to capture the semantics of the entities and relations within our training data,
we apply domain specific resources[2] to obtain the word embeddings and the
TransE model[1] to obtain KG embeddings for entities and relations in the KG.
We use these pre-trained Word embeddings and KG embeddings for entities and
relations to initialize the encoder and decoder embedding matrix, respectively,
and results show that this approach improves the overall performance.

3   Experiments
Data Sets We ran experiments on two public datasets NYT4 [4], ADE5 with se-
lected vocabularies and a Wiki-DBpedia dataset that is produced by distant
supervision6 . For data obtained by distant supervision, the test set is manually
labeled to ensure its quality. Each data set is an annotated corpus with corre-
sponding triples in the form of either s-p-o or entity mentions and relation
types at the sentence level. Details are available on our GitHub page.
                 Text Berlin is the capital city of Germany.
                 Triple dbr:Germany dbo:capital dbr:Berlin

    Table 1: Example annotated pair with distant supervision on Wiki-DBpedia

Evaluation Metrics We consider pipeline-based approaches that combine En-
tity Linking (EL) and Relation Classification (RC) as state of the art. We pro-
pose several baselines with combined outputs from state-of-the-art EL7 and RC
for evaluation. We use F1-measure to evaluate triple generation (an output is
considered correct only if s-p-o are all correct) in comparison with the baselines.

Baselines We implement multiple baselines including a classical supervised
learning using simple Lexical features, a state-of-the-art recurrent neural net-
work (RNN) approach with LSTM [3] and one with a Gate Recurrent Unit
(GRU) variant. Then we evaluate the performance on triple generation with re-
sults combining EL and RC. The hyper-parameters in our model are tuned with
10-fold cross-validation on the training set according to the best F1-scores. We
applied the same settings to the baselines. The details regarding the parameters
and settings are available on our GitHub page for replication purposes.

4   Result Analysis
We achieve the best F1 Measure of 84.3 on the triple generation from Table 2.
Note that the baseline approaches that we implemented are pipeline-based, and
thus they are very likely to propagate errors to downstream components. How-
ever, our model merges the two different tasks of EL and RC into one during the
4
  New York Times articles: https://github.com/shanzhenren/CoType
5
  Adverse drug events: https://sites.google.com/site/adecorpus
6
  http://deepdive.stanford.edu/distant_supervision
7
  Stanford, Domain specific NER
decoding, which composes a major advantage over pipeline-based approaches
that usually apply separate models on EL and RC. The most common errors
are caused by Out of vocabulary and Noise from overlapping relations
in text. As we do not cover all rare entity names or consider multiple triple
situations, these errors are valid in some sense.

                Tasks           NYT          ADE      Wiki-DBpedia
                Metric       F1-Measure F1-Measure F1-Measure
                EL+Lexical       36.8        61.4          37.8
                EL+LSTM          58.7        70.3          65.5
                EL+GRU           59.8        73.2          67.0
                Seq2Seq          64.2        73.4          73.5
                S+A+W+G          71.4        79.5          84.3

Table 2: Cross-dataset comparison on triple generations. Seq2Seq denotes the imple-
mentation of Seq2Seq without any attention mechanism and pre-trained embeddings;
A denotes attention mechanism; W and G denote pre-trained word embeddings for the
encoders and KG embeddings for the decoders, respectively.

5    Conclusions and Future Work
We present an end-end system for translating a natural language sentence to
its triple representation. Our system performs competitively on three different
datasets and our assumption on enhancing the model with pre-trained KG em-
beddings improves performance across the board. It is easy to replicate our work
and use our system following the demonstration. In the future, we plan to re-
design the decoder and enable the generation of multiple triples per sentence.
Acknowledgement This work was partially supported by the NIEHS Award
0255-0236-4609 / 1U2CES026555-01.

References
1. Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating
   embeddings for modeling multi-relational data. In: Advances in neural information
   processing systems. pp. 2787–2795 (2013)
2. Liu, Y., Ge, T., Mathews, K., Ji, H., McGuinness, D.: Exploiting task-oriented
   resources to learn word embeddings for clinical abbreviation expansion. Proceedings
   of BioNLP 15 pp. 92–97 (2015)
3. Miwa, M., Bansal, M.: End-to-end relation extraction using lstms on sequences and
   tree structures. arXiv preprint arXiv:1601.00770 (2016)
4. Ren, X., Wu, Z., He, W., Qu, M., Voss, C.R., Ji, H., Abdelzaher, T.F., Han, J.:
   Cotype: Joint extraction of typed entities and relations with knowledge bases. In:
   Proceedings of the 26th International Conference on World Wide Web. pp. 1015–
   1024 (2017)
5. Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural
   networks. In: Advances in neural information processing systems. pp. 3104–3112
   (2014)

</pre>