Archive for August, 2009

Google Translate: Swahili… bado kidogo

Thursday 27 August 2009

In the last couple of days Google has added Swahili to the list of languages supported by its Translate service. On one hand I’m very happy to see this addition as I think it has the potential to be a big step forward for development in east Africa. However, from first impressions the service still has a long way to go.

One of the main problems for Google is that Swahili is an agglutinative language – meaning that it puts morphemes (grammatical parts of words) together to form longer words. So it can be difficult for a machine to know where the morphemes (parts of the word carrying meaning) begin and end.

Here are some very simple examples that I tried putting into Google:

Swahili Morphemes English Google Translate
kupika ku-pika to cook cooking
ninapika ni-na-pika I am cooking I cooked
nilipika ni-li-pika I cooked I cooked
nitapika ni-ta-pika I will cook I cooked
sijapika si-ja-pika I have not cooked I cooked
apike a-pik-e let him cook apike
umepika u-me-pika you have cooked has cooked
tutapika tu-ta-pika we will cook we cooked
watakapopika wa-taka-po-pika when they will cook will kakopika
mlipokuwa mnapika m-li-po-kuwa m-na-pika when you (pl) were cooking as they were cooked
ikipikwa nasi i-ki-pik(w)a na-si if it is cooked by us it be boiled us
bado kidogo bado ki-dogo not quite yet still little

To be fair, from what I’ve seen the translations of single words isn’t bad at all. Where it falls down is in the grammar – translating Swahili past, present, future and negative-perfect tenses all to English past!

Going the other way, here a few English examples I tried:

English Swahili Google Translate English back-translation
many people watu wengi watu wengi many people
many trees miti mingi miti mingi many trees
many elephants tembo wengi wengi tembo many elephants
many cars magari mengi wengi magari many cars
I am cooking ninapika I am kupikia “I am” to cook with
I cooked nilipika mimi kupikwa I to be cooked
To be fair, from what I’ve seen the translations of single words isn’t bad at all. Kwa kweli, kutokana na yale ambayo nimeyaona, utafsiri wa maneno ya pekee siyo mbaya Kuwa na haki, kutokana na yale I’ve amemwona zote maneno ya wimbo sio mbaya wakati wote. In truth, coming from what “I’ve” he has seen all
words of song not bad all the time

At this point it looks to be a decent dictionary (although with nothing like the depth of the excellent Kamusi Project), and actually does ok with set phrases. However once you get past the set phrases that it knows it seems unable to understand the relatively simple grammar and come up with a meaningful translation.

This is obviously a work in progress, as the “Contribute a better translation” option shows. It would be interesting to know whether Google takes these user contributed translations and tries to work out how the grammars and structures of the languages compare, or whether it simply remembers the set translation in case anyone enters the exact same phrase again. The first would be fascinating to investigate, whereas I fear the second would be like trying to empty the ocean with a teaspoon.

Changing our Perspective

Monday 24 August 2009

In my job I have the privilege of listening to many people talk about their work around the world with minority language communities (as well as reading from quite a few others online). Recently I’ve realised that increasingly these presentations fall into two categories – those that really excite me, and those that really frustrate me.

I’ve been realising that the difference has nothing to do with what the person presents about, the work they’re doing or the way they go about the work. It doesn’t have anything to do with how successful the work has been, or the impact that has been made.

In fact the difference is much more subtle – so much so that I’m only just starting to put my finger on it. It’s all about the perspective of the person when they talk about the work they’re doing and the community that they’re working with.

The first type of person realises that, in explaining his work with a language community, he is a bridge between you (the audience) and the community. But he doesn’t feel any connection with the community – instead he tries to help you to relate to him. He tells you of the large cultural divide, but he does so in order that you can understand him and the difficulties that he has in his work. He puts you in his shoes.

The second type of person also realises that he is a bridge between you (the listeners) and the community. But unlike the first person he helps you to understand and relate to the community. He tells you of the immense cultural differences, but he does in order to help you to understand and identify with people. He puts you in their shoes.

But I think it goes deeper than just the things we say. The way we talk about people ultimately shows what our perspective is – how we perceive them, and what we believe about them.

The problem for the first person is that he sees things from an ethnocentric perspective. He doesn’t seem to respect the local people, or feel that they are his equals. He has come to help them, not to understand them. He sees many differences, and naturally is impacted most by the frustrations and difficulties. He doesn’t seem to notice however, that his cultural mistakes and blindspots are equally frustrating to his hosts.

He works productively, but always judges the success of his work, not by how the local people perceive him, but by what his friends “back home” think. He sees his value in the work that he can do and the tasks that he can accomplish before he returns home.

The second person views himself from the perspective of the people he is serving amongst. He doesn’t see them as different, but rather sees himself as different. He respects the local people, and is more aware of the cultural offense he may cause to them than the frustrations he feels. He sees cultural differences not as an obstacle to overcome, but as an opportunity to learn, albeit often very difficult lessons, from people who have a vast amount of wisdom.

He works hard, but realises that the real impact that he will make will be in and through the relationships that he forms within the community, not in the tasks that he completes. He sees himself just as one small part of a bigger picture – a picture that has been developing for hundreds of years, and will continue long after he leaves.

In my experience, almost without exception every westerner starts off in the first category. Maybe it’s the way our culture conditions us, or maybe it’s just human nature. But some will gradually have their whole world turned upside-down, to see things from a totally different perspective. For many this takes years, decades or even a lifetime.

Looking back to my 3 years in Tanzania, I can see in myself just about all the characteristics of the first person. I am embarrassed to think back over some of the me-centred things that I have thought and said when talking to people in the UK about “my work”.

Over the last couple of years I’ve had the privilege of listening to a number of people who have humbly come alongside minority language communities as equals, wanting to build genuine relationships and open to learning as much as teaching. I just hope some of their wisdom rubs off on me, and I can take a step back to see the true picture.